One 12-month program with four ways through it. Pick the flagship path or specialise in a single area.
The full 12-month path. Software engineering and fundamentals first, then LLMs, agents, RAG, MCP, cloud, evaluation and security, with a weekly 1:1 mentor from first month to placement.
Each track is eight modules you can follow on their own, or as your specialisation inside the 12-month program. Every track page has the full module list, the tools, and the roles it maps to.
Prompting, context engineering, structured output, model APIs, and the evaluation and cost work that turns a working demo into something a team can ship.
Chunking, embeddings, hybrid search, reranking and evaluation for retrieval-augmented generation, with the failure modes that show up once real users arrive.
The Model Context Protocol end to end: building tool servers, handling transport and auth, and connecting agents to real data without opening a security hole.
LangGraph is the framework for building agents as explicit state graphs instead of prompt chains that loop until something breaks. This course covers nodes, edges, state reduction, checkpointing, persistence and human-in-the-loop approval, then production concerns like streaming, retry semantics and testing graphs without a live model.
LangChain is the toolkit most LLM applications are built on: model abstractions, prompt templates, output parsers, document loaders, retrievers and tools. This course covers the components properly, when the library helps and when it is one abstraction too many, and how to keep a large chain readable and testable.
LLMOps is the practice of shipping, monitoring, evaluating and iterating on LLM systems in production. This course covers deployment patterns, versioning of prompts and models, offline and online evaluation, observability, cost and latency budgets, and the incident playbooks that decide whether a model change is safe to roll out.
AI system design is about the architecture around the model: retrieval, routing, caching, guardrails, fallbacks and the cost and latency tradeoffs between them. This course works through real designs end to end, from a support assistant at ten thousand requests a day to an agent platform with many tools, and covers the interview questions that come with them.
How the 12-month program compares with following one specialisation track.
| What | 12-month program | Single track |
|---|---|---|
| Format | 12 months, 18 modules | 8 modules, part of the 12-month path |
| Mentorship | Weekly 1:1, 12-14 months | Weekly 1:1, same mentor throughout |
| Projects | 6 production projects | 2 production projects + capstone |
| Interviews | Mock interviews until you can run them cold | Included in the full program |
| Placement support | Full, with referrals | Full, with referrals |
| Best for | Students starting from software fundamentals | Students who already know the basics |
Most students start with the 12-month program and specialise in month one. If you already have production experience, a single track is the faster route.
From first message to offer.
Tell us your branch, year and what you have built so far. We reply within two working days.
A 30-minute call to work out which track fits and whether the timing works for your semester.
Choose the specialisation in month one. If it is not right, switch without restarting the program.
Weekly modules, weekly calls, and production projects from month two onwards.
Mock interviews, resume work, and referrals where our mentor network has a real relationship.
Take the free assessment. It scores your current Python, DSA and AI knowledge and tells you which track to start with, plus what to learn first.
We take a fixed number of students each cohort so weekly mentorship stays 1:1. Tell us about your branch and what you have built so far, and we will reply within two working days.