RAG and Agents in 8 Weeks
Production RAG and multi-agent systems for software engineers to build retrieval pipelines and AI agents that hold up in the real world.
1 Enrolled

Vinay Kumar
AI Engineer & Educator
MS, IIT Kharagpur
Debjit Paul
Senior AI Researcher
PhD Heidelberg, Ex-EPFL
Trusted by 600+ engineers across US, India and rest of the world
Cohort Syllabus
Your instructors are Debjit Paul and Vinay Kumar.
Theory
- Core LLM terminology: tokens, context window, parameters, attention mechanism
- How LLMs are trained: pre-training, post-training, and inference at runtime
- Embeddings & semantic similarity: turning text into vectors
- Prompting basics: system, user, few-shot
Coding
- Make your first LLM API calls, and compute cosine similarity from scratch
1 more item
Theory
- Why RAG exists: knowledge cutoff and hallucination problem
- The 5-stage RAG pipeline: ingest → chunk → embed → index → retrieve
- Chunking strategies and when to use each
- Embedding models: choosing the right one for your use case
Coding
- Build an end-to-end RAG pipeline with LangChain + ChromaDB.
1 more item
Theory
- Why naive RAG hits accuracy ceilings
- Query rewriting techniques: expansion, HyDE, multi-query
- Cross-encoder reranking: LLM-quality scoring after initial retrieval
- Metadata filtering and hybrid search (dense + sparse)
Coding
- Apply advanced retrieval techniques to your Week 2 pipeline and benchmark accuracy improvements with an eval suite
1 more item
Theory
- Common pitfalls in production RAG systems
- GraphRAG: knowledge graphs as retrieval backends
- KAG (Knowledge-Augmented Generation): structured KB + LLM
- Agentic RAG: LLM decides what to retrieve, when, and how
Coding
- Build a GraphRAG system on a real use-case using Neo4j, and compare it against vanilla RAG
1 more item
Theory
- What is an agent? LLM + tools + loop
- LLM vs. Agent: how to distinguish pipeline vs single api call
- Tool / function calling: how the LLM triggers Python functions
- The ReAct pattern: Reasoning → Acting → Observing
Coding
- Build a single agent with tools, structured outputs, and basic guardrails.
1 more item
Theory
- Why multi-agent? Parallelism, specialisation, separation of concerns
- Agentic design patterns: Orchestrator-Worker, Routing
- Problems unique to multi-agent: orchestration, information isolation, planning
- Memory systems for agents: short-term and long-term
Coding
- Build a research + writer + critic multi-agent pipeline in LangGraph with routing.
1 more item
Theory
- Context engineering vs. prompt engineering
- What goes in the context: instructions, tools, history, retrieved docs
- Quantitative Evals (accuracy, F1, exact match, tool-call accuracy)
- Qualitative evals with LLM-as-a-Judge: rubric design, single-answer grading.
Coding
- Run a full eval suite on your Week 6 multi-agent pipeline with both quantitative and LLM-as-a-Judge evaluations
Theory
- AI engineering best practices: from prototype to production
- Engineering decision framework: choosing RAG type, agent pattern, and stack
- How to scope a capstone: MVP definition, what to cut, what to keep
- Architecture reviews and 1:1 feedback on each project plan
Coding
- Live capstone demos with peer Q&A, eval walkthroughs, and structured feedback
1 more item
Your Cohort Instructors

Debjit Paul
Senior Researcher at a leading global AI lab | PhD, Heidelberg | Ex-EPFL
Debjit is a Senior Researcher at a leading global AI lab, working on AI and NLP. He earned his PhD in Computer Science from Heidelberg University (summa cum laude) and was a Postdoctoral Researcher at EPFL, Switzerland, improving the reasoning abilities of LLMs. Before that, he built deep-research AI agents for multi-step reasoning, retrieval and synthesis at Huawei's research lab in London. His work is published at ACL, EMNLP, EACL and ICLR, including DeepSynth, a benchmark for evaluating LLM agents.
Vinay Kumar
AI Engineer & Educator | MS, IIT Kharagpur | Senior Technical Trainer, IIT Madras
Vinay is an AI engineer and educator with 13+ years across data science, NLP, Generative AI and Agentic AI. He holds an MS by Research from IIT Kharagpur (CGPA 9.69/10), where his work on NLP and information retrieval was published in IEEE. He previously led Data Science Research at SyTrue, building production NLP systems on clinical records for health plans and providers. Today he teaches Agentic AI at IIT Madras's Pravartak program and is an Adjunct Professor of Practice at Atria University, covering RAG, multi-agent systems, LangGraph, MCP, evaluation and LLMOps.
Cohort Investment
$1,400
Cohort Starts On Jan 2, 2027
- 12 Live Classes with Instructors
- 5 Live Networking sessions
- Hands-on production capstone project
- 45 days of teacher support
- Lifetime access to recordings and material
- Certificate of Completion
7-day money-back guarantee
Learn how to reimburse this programFrequently asked questions
This program is for software engineers who want to build production-grade AI systems. We expect prior coding experience and a basic understanding of software systems.
This cohort focuses on AI engineering, specifically LLMs and their applications. We cover some basic math and ML concepts, just enough to understand LLMs in depth.
Yes, you will have lifetime access to all video recordings and reading material for this cohort.
We offer a 7-day money-back guarantee. If you are not satisfied with the program, you can request a refund within 7 days of the program start date. Contact our support team for a refund. Please note that payment gateway and currency charges will be non-refundable (~5-10% of invoice value).
Classes will be held every week at 9 AM - 10:30 AM IST, on Saturday and Sunday. We will also have networking sessions on Wednesday from 7 - 8 PM IST.
We provide a GSTIN invoice, course completion certificate, and clarifications to your team manager and HR if needed. You can download the Cohort Brochure here and find our email template for reimbursement here.
The classes require 3 hours per week to attend. We expect a student to study for 3 hours per week outside of class. The total time commitment is 6-8 hours per week.
We expect all students to have coding experience in at least one programming language. Prior software engineering experience is helpful. All other prerequisites for ML and Math are included in the cohort.

