Apply Now
Hands-on exposure to leading LLM APIs, open-source models, agent frameworks, vector databases, and deployment tooling.
*Some of the tools mentioned above may be replaced with newer or updated tools based on evolving market conditions. Such decisions shall be made at the sole discretion of the University.
6 months · 30+ live classes · built for developers. Working knowledge of Python helps - Module 1 includes a Python refresher, and no prior GenAI experience is needed.
Understand LLMs and APIs deeply and build production-style GenAI applications without frameworks - with clarity on how GenAI systems work under the hood.
Your first GenAI Python script · one chatbot compared across API, open-source and local models · a memory + UI chatbot with zero frameworks.
Learners can design and build production RAG systems that answer accurately over private knowledge bases, and choose the right vector store for scale, latency and cost.
A RAG assistant answering over a 100-page corpus with citations, backed by a hybrid semantic search engine.
Learners can build autonomous agents that reason and call tools, then orchestrate teams of specialised agents to solve complex, real-world workflows.
A multi-agent system where planner, researcher and writer agents collaborate on a report.
Learners can measure, safeguard, containerise and deploy AI applications to production standards.
Deploy an AI application to the cloud with a public API and a monitoring dashboard.
Learners finish with a deployed portfolio, an optimised professional profile and the interview readiness to target AI engineering roles.
Publish your capstone with full documentation and present it in a mentor-reviewed showcase.
Practitioners who build and deploy AI in production, bringing real industry experience into every live session.
Practical way of teaching, with hands-on examples and live coding, helps us a lot to understand both the concepts and the applications. Thank you, sir!
See what previous batch learners have built, and what you'll ship to your own portfolio.
Build your first LLM chatbot with a clean Streamlit interface and conversation memory that keeps context across turns.
Fine-tune a Microsoft Phi model on your own laptop with LoRA/QLoRA adapters, 4-bit quantization and merged-adapter inference.
A production-grade RAG assistant - ingestion, embeddings, semantic retrieval, grounded answers and multi-session memory.
An LLM pipeline that classifies support calls, routes them through evaluation chains, and generates structured QA reports.
Specialized LangGraph agents that turn a natural-language requirement into a complete software project - plan, code, test, review.
Turn call recordings and documents into analytics-ready insights with multimodal LLMs, retries, rate limits and cost tracking.
Serve Llama models on EC2 with Ollama, exposed as a production REST API with FastAPI, Docker and deployment automation.
Hybrid BM25 + vector search, contextual compression and reranking - monitored end-to-end with LangFuse or LangSmith.
Collaborating agents for planning, web search, extraction, synthesis and fact-checking - orchestrated with LangGraph and MCP.
Every project contributes to a professional GitHub portfolio, with later-stage projects deployed to the cloud.
Awarded by the Continuing Education Programme of an Institute of National Importance.
Unique certificate & enrolment number you can share on LinkedIn and with employers.
Granted on completion of 6 months of live instruction and a faculty-reviewed capstone.
Every live class recorded · dedicated community platform · AMA sessions with industry mentors
Most employers reimburse upskilling like this. We hand you everything your company needs to sign off, no chasing, no awkward asks.
Get reimbursed