GA
GenAI for Developers
LLMs · Prompting · RAG · LLMOps — 8 Weeks
8 Weeks Hands-On Project-Driven

GenAI for Developers

Build production-capable GenAI skills: understand Large Language Models, craft robust prompts, implement RAG pipelines, and apply LLMOps best practices.

Duration: 8 weeks
Format: Live labs + recorded content
Effort: 8–12 hours/week

Program Overview

This 8-week program is designed for developers and ML practitioners moving from experimentation to production-ready GenAI applications. Learn LLM fundamentals, prompt engineering, vector search & RAG, system design, cost & safety optimisation, and deployment patterns used in production.

Core Topics

  • LLM fundamentals: architectures, tokenization, context windows, inference patterns
  • Prompt engineering: templates, chaining, grounding, evaluation
  • RAG pipelines: vector embeddings, similarity search, chunking, retrieval strategies
  • LLMOps basics: monitoring, cost-control, model selection, caching, CI for prompts
  • Safety & alignment: hallucinations, guardrails, content filtering, secure data handling
  • Deployment: building inference APIs, batching, scaling, lightweight serving
  • Open-source & hosted tools: embeddings libraries, vector stores, orchestration patterns

Who should join?

Backend/frontend developers, ML engineers, technical product managers, or anyone building products with LLMs. Comfortable reading/writing Python/JS and basic ML concepts recommended.

Prerequisites

  • Programming in Python or JavaScript
  • REST APIs & basic ML familiarity
  • Laptop with internet; ability to run lightweight Python environments

Outcomes & Career Support

  • 3+ hands-on projects (RAG app, prompt evaluation suite, deployed inference service)
  • Capstone: end-to-end GenAI app with retrieval, prompt flow, deployment
  • Technical profile & demo guidance for interviews
  • Completion certificate & technical report

8-Week Curriculum

Each week combines live labs, exercises, and mini-projects.

Week 1 — LLM Foundations
Model families, tokenization, prompt lifecycle, latency & cost considerations.
Week 2 — Prompt Engineering
Prompt patterns, templates, few-shot prompting, chain-of-thought, evaluation metrics.
Week 3 — Embeddings & Vector Search
Embedding models, similarity metrics, vector indexes, nearest neighbors.
Week 4 — RAG
Chunking, context assembly, hybrid retrieval, latency tradeoffs.
Week 5 — Building RAG Applications
End-to-end pipeline: ingestion, indexing, retrieval, prompting, output handling.
Week 6 — LLMOps & Reliability
Monitoring, prompt/version control, caching, cost optimization, model selection.
Week 7 — Safety, Alignment & Scaling
Mitigating hallucinations, content filtering, guardrails, privacy-preserving retrieval.
Week 8 — Capstone & Deployment
Finalize capstone, deploy demo API/UI, performance tests, project presentation.

Capstone & Projects

End-to-end GenAI application integrating retrieval, prompts, and deployment.

Sample Project Ideas

  • Knowledge assistant over product docs with conversational interface
  • Automated code assistant with context-aware retrieval
  • Document summarization + Q&A pipeline with evaluation metrics

Assessment

Weekly labs, code reviews, mid-program checkpoint, final capstone evaluation and technical report.

How to Apply

  1. Fill out the application form with your basic details and background information.
  2. Complete the course payment of ₹9,500/- to confirm your enrollment. Multiple payment options are available.
  3. Receive your official admission letter after payment confirmation.
  4. Start attending classes, available both online and offline according to your preference.

Refund & Cancellation

Full refund if cancelled within 7 days of enrollment and before course start. Contact admissions for details.

Application Form