Learn by Doing. Think Like an AI Engineer.

LLM Overview and Foundations

• Data collection (manual crawling, Common Crawl)
• Data cleaning (RefinedWeb, Dolma, FineWeb)
• Tokenization (e.g., BPE)
• Architecture (neural networks, Transformers, GPT family, Llama family)
• Text generation (greedy and beam search, top-k, top-p)

• SFT
• RL and RLHF (verifiable tasks, reward models, PPO, etc.)

• Traditional metrics
• Task-specific benchmarks
• Human evaluation and leaderboards

Overview of Adaptation Techniques

• Parameter-efficient fine-tuning (PEFT)
• Adapters and LoRA

• Few-shot and zero-shot prompting
• Chain-of-thought prompting
• Role-specific and user-context prompting

RAGs Overview

• Document parsing (rule-based, AI-based) and chunking strategies
• Indexing (keyword, full-text, knowledge-based, vector-based, embedding models)

• Search methods (exact and approximate nearest neighbor)
• Prompt engineering for RAGs

RAFT: Training technique for RAGs

Evaluation (context relevance, faithfulness, answer correctness)

• Agents vs. agentic systems vs. LLMs
• Agency levels (e.g., workflows, multi-step agents)

• Prompt chaining
• Routing
• Parallelization (sectioning, voting)
• Reflection
• Orchestration-worker

• Tool calling
• Tool formatting
• Tool execution
• MCP

• Planning autonomy
• ReACT
• Reflexion, ReWOO, etc.
• Tree search for agents

Multi-Agent Systems (challenges, use-cases, A2A protocol)

• Overview of reasoning models like OpenAI's "o" family and DeepSeek-R1

• Inferece-time scaling
• CoT prompting
• Self-consistency
• Sequential revision
• Tree of Thoughts (ToT)
• Search against a verifier

• SFT on reasoning data (e.g., STaR)
• Reinforcement learning with a verifier
• Reward modeling (ORM, PRM)
• Self-refinement
• Internalizing search (e.g., Meta-CoT)

• VAE
• GANs
• Auto-regressive models
• Diffusion models

• Data preparation
• Diffusion architectures (U-Net, DiT)
• Diffusion training (forward process, backward process)
• Diffusion sampling
• Evaluation (image quality, diversity, image-text alignment, IS, FID, and CLIP score)

• Latent-diffusion modeling (LDM) and compression networks
• Data preparation (filtering, standardization, video latent caching)
• DiT architecture for videos
• Large-scale training challenges
• T2V's overall system

• Choose your own idea
• Build with techniques from the course
• Get real-time feedback from the instructor as you build
• Demo + feedback session

Gear up for 50%+ UI code generation with the help of AI.

• React or Next.js structure, routing, and TypeScript basics
• Component patterns, composition, and state management choices
• Design tokens, theming, and accessible UI defaults

• Responsive layouts, performance budgets, and image strategies
• Forms, validation, and error states users actually see

Generate most of your architecture plan and backend code with AI.

• REST and GraphQL trade-offs; versioning and error contracts
• Auth patterns: sessions, JWT, OAuth basics, and secure cookies

• Relational modeling, migrations, and ORM usage
• Transactions, idempotency, and background jobs when you need them

• Wiring the UI to APIs with loading, retries, and optimistic updates

Pair-programming, codegen, and agentic AI—moving from suggestions to systems that can own multi-step work like an independent developer when you want them to.

• Autonomous planning, tool use, and long-running tasks—not just line-by-line completions
• How agentic workflows can take over feature slices end-to-end, and where human review still matters

• Copilot, Cursor, and chat-to-code: effective prompts for your stack
• Generating tests, types, and refactors from specs and diffs

• Reviewing AI output: security, licensing, and correctness checks
• When to hand-write vs. when codegen wins (and how to mix both)

• PR descriptions, CI comments, and keeping humans in the loop

Workflow Automation for Engineers

• Node and shell scripts for repeatable tasks and one-command setups
• Linting, formatting, and pre-commit hooks that stick

• Pipelines: test, build, preview deploys, and promotion patterns
• Secrets, environments, and safe rollbacks

• Webhooks, bots, and MCP-style tool use for dev productivity
• When to reach for low-code automation vs. custom code

Practical AI in Apps

• Lightweight RAG or tool-backed flows in your existing UI
• Streaming responses, cancellation, and loading affordances

• Rate limits, quotas, logging, and cost awareness in production
• Privacy, data retention, and user-facing disclosures

• Evaluating AI features: offline checks plus live monitoring

• Propose an idea that combines UI, APIs, and at least one automation or AI touchpoint
• Ship iteratively with instructor feedback on architecture and trade-offs
• Demo day: walk through flows, ops story, and what you would automate next