Generative AI & LLM Engineering
Engineer production-ready AI agents, RAG pipelines, and LLM applications.
12 Weeks
6–8 hours / week
Intermediate
Live Cohort
Who is this program for?
- Software engineers looking to build AI-native applications and microservices
- Developers wanting to master RAG, Vector Databases, and AI Agents
- Technical builders wanting to move beyond basic ChatGPT prompt wrappers
Prerequisites & Requirements
Basic Python programming skills and familiarity with web APIs.
Technologies You Will Master
Curriculum Breakdown
Master prompt engineering, API paradigms, and JSON schema extraction.
- LLM architecture basics: Context windows, temperature, and token economics
- Advanced prompt patterns: Few-shot, Chain-of-Thought, and ReAct prompting
- Function calling, tool definitions, and schema validation with Pydantic
- Model evaluation benchmarks, latency mitigation, and cost optimization
Real Projects You Will Build
All capstones are reviewed line-by-line by senior tech mentors and deployed to live cloud environments.
Enterprise Multi-Document RAG Assistant
Hybrid search document retrieval engine
Document analysis pipeline processing PDFs and Markdown with hybrid vector search, chunk reranking, and citation generation.
Autonomous Research & Code Agent
Multi-step tool-calling agent with memory
Stateful agent built with LangGraph that searches documentation, executes Python scripts in a sandbox, and writes test suites.
Local LLM Inference Microservice
Private offline AI inference API
Containerized FastAPI microservice orchestrating quantized open-weights models (Ollama/vLLM) with prompt caching.
Frequently Asked Questions
Generative AI & LLM Engineering
Includes live interactive sessions, mentor code reviews, capstone projects, and alumni referral access.