AI Engineering

Curriculum: Module 1: Production Python, Async & PyTorch Foundations - High-performance Python, asynchronous workflows, and vectorization (NumPy) - Deep Learning fundamentals, tensor operations, and model architectures in PyTorch Module 2: Foundation Models & API Orchestration - Architecting with OpenAI, Anthropic, and open-source models (Hugging Face) - Structured outputs, function calling, schema validation, and guardrails Module 3: Retrieval-Augmented Generation (RAG) & Vector Databases - Semantic search, embeddings, document chunking, and hybrid search - Hands-on integration with pgvector, Qdrant, and ChromaDB Module 4: Autonomous Agents & Tool Usage - Building multi-step agentic systems and tool integration using LangGraph - Agent memory state, reflection loops, and tool-calling validation Module 5: Fine-Tuning & Quantization - Fine-tuning open-source LLMs (Llama, Mistral) using LoRA / QLoRA - Quantization strategies and efficient local model evaluation Module 6: Production MLOps, APIs & Deployment - Exposing model endpoints with high-performance FastAPI services - Containerization with Docker, API rate-limiting, monitoring, and cloud deployment