ENROLLING NOWLIVE COHORT PROGRAM

LLM Engineering: From Tokens to Production

Master the full stack of LLM development — from transformer internals to production deployment. Build real systems, not toy examples.

20 sessions10 weeks12 seats remaining
Enroll Now View Curriculum

What You'll Learn

Build production RAG systems from scratch
Fine-tune models with LoRA/QLoRA on custom data
Deploy agentic systems with tool use & MCP
Implement evaluation frameworks (evals + LLM-as-Judge)
Scale inference with KV cache, quantization, and streaming
Capstone: End-to-end production AI system

Curriculum — 20 Sessions

Week 1-2

Foundations

LLM Architecture Deep Dive

Transformers, attention, embeddings, next-token prediction.

📖 transformer📖 attention
Tokenization & Context Windows

BPE, SentencePiece, context limits, prompt budgeting.

📖 tokenization📖 context window

Week 3-4

Training & Fine-Tuning

Pre-training at Scale

Data pipelines, distributed training, scaling laws.

📖 pre training📖 scaling laws
Fine-Tuning with LoRA

Parameter-efficient fine-tuning, data preparation, evaluation.

📖 fine tuning📖 lora and peft
Alignment: RLHF & DPO

Human preference learning, reward modeling, direct preference optimization.

📖 rlhf📖 dpo

Week 5-6

RAG & Retrieval Systems

RAG Architecture & Patterns

Embedding models, vector stores, chunking strategies.

📖 rag📖 embeddings
Advanced RAG

Hybrid search, re-ranking, multi-modal RAG, evaluation with RAGAS.

📖 grounding

Week 7-8

Agents & Tool Use

Agent Architectures

ReAct, tool use, function calling, structured output.

📖 agent📖 tool use and function calling
MCP & Multi-Agent Systems

Model Context Protocol, orchestration, production patterns.

📖 mcp📖 workflow

Week 9-10

Production & Capstone

Production Deployment

Serving, scaling, monitoring, KV cache optimization.

📖 inference📖 kv cache📖 streaming
Evaluation & Guardrails

Evals, LLM-as-Judge, safety guardrails, prompt injection defense.

📖 evals📖 guardrails
Capstone Presentations

Final project demo, peer review, feedback.

Enrollment

₹25,000/ $299
  • 20 live sessions (recorded for replay)
  • Capstone project with feedback
  • Peer cohort access
  • Certificate of completion
  • 15-day full refund guarantee

12 seats remaining · Starts August 9, 2026

Frequently Asked Questions

What are the prerequisites?
Basic Python programming and familiarity with ML concepts. No deep learning experience required — we start from fundamentals.
What if I miss a live session?
All sessions are recorded and available within 24 hours. You can watch at your own pace, but live attendance is strongly encouraged for Q&A.
Is there a refund policy?
Yes — 15-day full refund guarantee. If the program isn't right for you, get a complete refund within the first 15 days.
What's the time commitment?
Approximately 8-10 hours per week: 2-3 hours live session + 5-7 hours of assignments, reading, and project work.
Will I get a certificate?
Yes — upon completing the capstone project, you receive a certificate of completion.