Generative AI & LLM Engineering
LLM APIs, RAG, autonomous agents and fine-tuning — build and ship real generative AI applications, not toy demos.
- 24 weeks
- 8 gates
- Full-time, on-site
- Beginner to job-ready
What you'll actually learn
Week by week, tool by tool, gate by gate. No vague module names, and no way to slide past a week you haven't cleared.
Weeks 01–02 Python & LLM API Foundations
Python for AI, virtual environments, and integrating multiple LLM providers with structured, streaming responses.
GateA multi-provider LLM wrapper with streaming, built from scratch.
Weeks 03–04 Prompt Engineering & Embeddings
Advanced prompting techniques — Chain-of-Thought, ReAct — plus the mathematical foundations of vector embeddings.
GateA semantic search engine prototype using real embeddings.
Weeks 05–07 Vector Databases & RAG
Production vector storage and retrieval-augmented generation, from a first pipeline to re-ranked, contextually compressed retrieval.
GateAn advanced RAG pipeline scoring 85%+ retrieval accuracy.
Weeks 08–11 Agent Frameworks & Tool Use
LangChain and LlamaIndex in depth, function calling, and autonomous multi-agent systems with LangGraph.
GateA multi-agent system performing a complex, multi-step workflow.
Weeks 12–16 Evaluation, Fine-Tuning & Guardrails
Tracing and evaluating LLM output, self-hosting open-source models, LoRA fine-tuning, and hardening against misuse.
GateA hardened, self-hosted fine-tuned model with active safety guardrails.
Weeks 17–18 Full-Stack & Multimodal AI
Connecting an AI backend to a real-time streaming frontend, and integrating vision and speech models.
GateA full-stack AI application with a live streaming chat interface.
Weeks 19–23 Capstone
Design, build and deploy a production GenAI application end to end, then audit its latency and token cost.
GateA live, cost-optimised production GenAI application.
Week 24 Final Gate & Graduation Defense
Defend the full capstone architecture live, including an on-the-spot code modification.
GateClear the final GenAI gate examination.
Want the full week-by-week syllabus?
Get the complete breakdown as a PDF — every module, tool, and gate.
Questions people ask
Do I need a coding background?
No. Every track — Data Engineering, Generative AI, both full-stack tracks, Data Analytics, and QA — starts from the fundamentals in its first week. If you're unsure which track fits you, the track fit conversation will sort it out.
Is this online or offline?
Offline — every track is full-time, in person, at our Kochi centre.
What are the batch timings?
Intake opens every Monday — your cohort is simply the Monday you start.
Can I pay in instalments?
Yes — a registration payment to confirm your seat, then five monthly instalments, the first due two weeks after your first week starts.
What's your refund policy?
Free to leave in your first 7 days — everything back, including registration. After that, registration is non-refundable, and tuition is refunded on a sliding scale based on the highest gate you've cleared: 50% through Gate 3, 25% through Gates 4–6, and nothing after Gate 6.
Every job track we run
- Data Engineering29 weeks · 15 gates
- Generative AI & LLM Engineering24 weeks · 8 gates
- Full-Stack Development with Python24 weeks · 8 gates
- Full-Stack Web Development (MERN)24 weeks · 8 gates
- Full-Stack Web Development (MEAN)24 weeks · 8 gates
- Data Analytics & BI with Power BI24 weeks · 8 gates
- Software Testing & QA Automation24 weeks · 8 gates
Not sure which track fits? Join the waitlist and we'll tell you.
Join the waitlist and we'll come back with a straight answer — including telling you if Anaxion isn't the right fit for what you're trying to do.
- Free to join
- Reply in one working day
- No obligation
Generative AI & LLM Engineering