AI Engineering: Building LLMs & Neural Networks Curriculum

Public curriculum preview for visitors and enrolled students. Use this page to evaluate module scope, outcomes, and learning path.

Download PDFBack to Course
Curriculum

AI Engineering: Building LLMs & Neural Networks

Structured, hands-on learning path for AI Engineering: Building LLMs & Neural Networks with detailed weekly outcomes and practical delivery.

Duration: 16 Weeks
Level: Advanced
Study Time: 2 hours/week + labs
School: Hexadigitall Academy
16 WeeksAdvancedProject-Based

Welcome to AI Engineering: Building LLMs & Neural Networks! 🎓

This curriculum for AI Engineering: Building LLMs & Neural Networks follows a Bloom-aligned progression from practical foundations to measurable professional outcomes, with weekly evidence, labs, and portfolio outputs matched to advanced expectations.

Each week advances from comprehension and application toward evaluation and creation, ensuring progressive learning and capstone readiness.

Your success is our priority. By the end, you will produce portfolio-ready artifacts and confidently explain your technical decisions. You will graduate with a professionally curated portfolio that demonstrates scope, depth, and delivery quality. You will graduate with a professionally curated portfolio that demonstrates scope, depth, and delivery quality. You will graduate with a professionally curated portfolio that demonstrates scope, depth, and delivery quality. You will graduate with a professionally curated portfolio that demonstrates scope, depth, and delivery quality.

Prerequisites

  • Python programming proficiency: libraries (NumPy, Pandas, scikit-learn), data structures, and API usage
  • Statistics and probability fundamentals: distributions, hypothesis testing, and experimental design
  • Machine learning basics: supervised learning, hyperparameter tuning, and model evaluation metrics
  • Hands-on experience with notebooks (Jupyter), experiment tracking, and model versioning systems

Essential Resources

  • Model development workflow guides, hyperparameter tuning references, and experiment tracking templates
  • Feature engineering playbooks, model evaluation metrics library, and production deployment checklists
  • Research paper repository, implementation examples, and performance benchmarking tools

Complementary Courses

LLMs & Generative AI

Master fine-tuning, prompt engineering, and RAG architecture patterns

MLOps & Model Deployment

Learn model serving, A/B testing, and continuous model improvement workflows

Production AI Systems

Deepen model monitoring, drift detection, and operational governance

Learning Roadmap

  • Early Weeks: ML fundamentals, data preparation, and baseline models
  • Middle Weeks: Advanced model techniques, experimentation, and tuning
  • Late Weeks: Production deployment, monitoring, and continuous improvement

Detailed Weekly Curriculum

Each week includes outcomes and practical lab work aligned to the curriculum structure.

Week 1

AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 1)

2 hours + labs
Learning Outcomes
  • Analyze the principles of AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 1) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Evaluate AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 1) in a guided scenario using realistic tools, constraints, and quality gates.
  • Design trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 1), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 1) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 1), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 1) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 1) across failure and recovery scenarios.
Week 2

AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 1)

2 hours + labs
Learning Outcomes
  • Analyze the principles of AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 1) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Evaluate AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 1) in a guided scenario using realistic tools, constraints, and quality gates.
  • Design trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 1), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 1) with measurable success criteria and next actions.
Lab Exercise
  • Build a release workflow for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 1) with automated checks, approvals, and artifact traceability.
  • Implement quality and security gates for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 1) and enforce fail-fast criteria.
  • Execute a staged promotion for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 1) and validate rollback safety under a controlled failure.
Week 3

AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 1)

2 hours + labs
Learning Outcomes
  • Analyze the principles of AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 1) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Evaluate AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 1) in a guided scenario using realistic tools, constraints, and quality gates.
  • Design trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 1), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 1) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 1), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 1) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 1) across failure and recovery scenarios.
Week 4

AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 1)

2 hours + labs
Learning Outcomes
  • Analyze the principles of AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 1) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Evaluate AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 1) in a guided scenario using realistic tools, constraints, and quality gates.
  • Design trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 1), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 1) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 1), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 1) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 1) across failure and recovery scenarios.
Week 5

AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 1)

2 hours + labs
Learning Outcomes
  • Analyze the principles of AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 1) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Evaluate AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 1) in a guided scenario using realistic tools, constraints, and quality gates.
  • Design trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 1), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 1) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 1), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 1) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 1) across failure and recovery scenarios.
Week 6

AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 1)

2 hours + labs
Learning Outcomes
  • Analyze the principles of AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 1) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Evaluate AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 1) in a guided scenario using realistic tools, constraints, and quality gates.
  • Design trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 1), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 1) with measurable success criteria and next actions.
Lab Exercise
  • Instrument AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 1) with metrics, logs, and tracing hooks aligned to service objectives.
  • Create actionable alerts for AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 1) and test escalation paths using simulated incidents.
  • Perform root-cause analysis for a AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 1) failure scenario and document corrective actions.
Week 7

AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 1)

2 hours + labs
Learning Outcomes
  • Evaluate the principles of AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 1) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Design AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 1) in a guided scenario using realistic tools, constraints, and quality gates.
  • Optimize trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 1), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 1) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 1), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 1) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 1) across failure and recovery scenarios.
Week 8

AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 1)

2 hours + labs
Learning Outcomes
  • Evaluate the principles of AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 1) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Design AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 1) in a guided scenario using realistic tools, constraints, and quality gates.
  • Optimize trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 1), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 1) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 1), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 1) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 1) across failure and recovery scenarios.
Week 9

AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 2)

2 hours + labs
Learning Outcomes
  • Evaluate the principles of AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 2) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Design AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 2) in a guided scenario using realistic tools, constraints, and quality gates.
  • Optimize trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 2), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 2) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 2), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 2) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 2) across failure and recovery scenarios.
Week 10

AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 2)

2 hours + labs
Learning Outcomes
  • Evaluate the principles of AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 2) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Design AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 2) in a guided scenario using realistic tools, constraints, and quality gates.
  • Optimize trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 2), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 2) with measurable success criteria and next actions.
Lab Exercise
  • Build a release workflow for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 2) with automated checks, approvals, and artifact traceability.
  • Implement quality and security gates for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 2) and enforce fail-fast criteria.
  • Execute a staged promotion for AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 2) and validate rollback safety under a controlled failure.
Week 11

AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 2)

2 hours + labs
Learning Outcomes
  • Evaluate the principles of AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 2) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Design AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 2) in a guided scenario using realistic tools, constraints, and quality gates.
  • Optimize trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 2), then record rationale for stakeholder review.
  • Justify a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 2) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 2), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 2) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 2) across failure and recovery scenarios.
Week 12

AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 2)

2 hours + labs
Learning Outcomes
  • Design the principles of AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 2) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Optimize AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 2) in a guided scenario using realistic tools, constraints, and quality gates.
  • Architect trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 2), then record rationale for stakeholder review.
  • Defend a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 2) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 2), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 2) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Experiment Tracking and Reproducibility (Sprint 2) across failure and recovery scenarios.
Week 13

AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 2)

2 hours + labs
Learning Outcomes
  • Design the principles of AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 2) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Optimize AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 2) in a guided scenario using realistic tools, constraints, and quality gates.
  • Architect trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 2), then record rationale for stakeholder review.
  • Defend a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 2) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 2), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 2) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 2) across failure and recovery scenarios.
Week 14

AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 2)

2 hours + labs
Learning Outcomes
  • Design the principles of AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 2) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Optimize AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 2) in a guided scenario using realistic tools, constraints, and quality gates.
  • Architect trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 2), then record rationale for stakeholder review.
  • Defend a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 2) with measurable success criteria and next actions.
Lab Exercise
  • Instrument AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 2) with metrics, logs, and tracing hooks aligned to service objectives.
  • Create actionable alerts for AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 2) and test escalation paths using simulated incidents.
  • Perform root-cause analysis for a AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 2) failure scenario and document corrective actions.
Week 15

AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 2)

2 hours + labs
Learning Outcomes
  • Design the principles of AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 2) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Optimize AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 2) in a guided scenario using realistic tools, constraints, and quality gates.
  • Architect trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 2), then record rationale for stakeholder review.
  • Defend a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 2) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 2), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 2) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 2) across failure and recovery scenarios.
Week 16

AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 2)

2 hours + labs
Learning Outcomes
  • Design the principles of AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 2) and link them to course outcomes at advanced depth with architecture-level decision quality.
  • Optimize AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 2) in a guided scenario using realistic tools, constraints, and quality gates.
  • Architect trade-offs, risks, and decision points for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 2), then record rationale for stakeholder review.
  • Defend a portfolio-ready delivery strategy memo for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 2) with measurable success criteria and next actions.
Lab Exercise
  • Build and validate topology for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 2), including segmentation and routing intent.
  • Implement policy controls for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 2) traffic paths and verify allowed/denied flows.
  • Run connectivity and resilience tests for AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 2) across failure and recovery scenarios.

Capstone Projects

Project 1: AI Engineering: Building LLMs & Neural Networks Foundation Build

Deliver a concrete foundation implementation covering the first phase of the curriculum.

  • Implement and validate AI Engineering: Building LLMs & Neural Networks: ML Problem Framing and Baselines (Sprint 1).
  • Integrate AI Engineering: Building LLMs & Neural Networks: Feature Engineering and Data Pipelines (Sprint 1) with reusable workflow standards.
  • Publish evidence for AI Engineering: Building LLMs & Neural Networks: Model Training and Evaluation (Sprint 1) with test and quality artifacts.

Project 2: AI Engineering: Building LLMs & Neural Networks Integrated Systems Build

Combine mid-program competencies into a production-style integrated workflow.

  • Build an end-to-end flow around AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 1) and AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 1).
  • Add controls, observability, and rollback paths for reliability.
  • Document architecture decisions and trade-offs tied to AI Engineering: Building LLMs & Neural Networks: Production Hardening and Rollback (Sprint 1).

Project 3: AI Engineering: Building LLMs & Neural Networks Capstone Delivery

Ship a portfolio-ready capstone with measurable outcomes and stakeholder-ready presentation.

  • Deliver a complete implementation centered on AI Engineering: Building LLMs & Neural Networks: Model Serving and API Integration (Sprint 2).
  • Validate readiness for AI Engineering: Building LLMs & Neural Networks: Monitoring, Drift, and Reliability (Sprint 2) using objective acceptance checks.
  • Present final defense and roadmap based on AI Engineering: Building LLMs & Neural Networks: Responsible AI and Governance (Sprint 2) outcomes.