Rishav Kumar
Principal Data Analyst
Intermediate to Job-Ready
Generative AI Program
Master LLMs, RAG & Agentic Workflows — Build 3 Real AI Products
A 3-month, 78-hour weekend program covering LLMs, prompt engineering, LangChain, RAG, agentic AI, evaluation and deployment. Build 3 portfolio-ready AI products across 5 phases.
- 3 Months · 13 Weeks · 78 Hours
- Live weekend cohort (Sat & Sun) + recordings
- Live instructor-led on Zoom
- 1-year placement support
Enrol online
₹19,999₹39,999
or ₹950/month with EMI
Secure checkout via Razorpay — UPI, cards, netbanking and wallets. Instant access in your dashboard.
Next cohort starts in
--Days
--Hours
--Minutes
--Seconds
Batch begins 26 September 2026
Talk to a mentor
Get the detailed syllabus, batch dates and fee options.
Overview
What this program covers
Master LLMs, RAG & Agentic Workflows — Build 3 Real AI Products. 78 hours of live core training across 13 weeks, delivered on Saturdays and Sundays. Built for developers with basic Python, data professionals adding AI, career switchers moving into AI engineering and professionals boosting productivity with AI.
This program is for you if:
- You're a developer or engineer with basic Python wanting to build real AI products
- You're a data professional adding LLMs, RAG and agentic AI to your toolkit
- You're a career switcher moving into AI engineering with some coding background
- You're a professional boosting productivity by building AI-powered workflows
Outcomes
What you will be able to do
Work confidently with LLM APIs, tokens, embeddings and structured outputs
Design reliable prompts with zero-shot, few-shot and chain-of-thought techniques
Build LangChain applications with chains, agents, memory and tool-calling
Ship production-style RAG pipelines with vector databases and semantic search
Evaluate AI systems for hallucination, retrieval quality and responsible AI risks
Deploy 3 real AI products live with FastAPI/Streamlit and present them in interviews
Meet your instructors
Learn directly from working data professionals
Varsha Sathya
AI Engineer
Student success stories
Real career transformations from Skillancy alumni
“One of the most impactful learning experiences of my journey — especially SQL and Python. Real-world scenarios and case studies strengthened my analytical thinking.”
Sanghamitra Phukan
Oracle
“Skillancy's mentorship went beyond interview prep — teaching me how to think critically and solve real-world problems, with end-to-end support throughout.”
Jayant Khanna
PayPal
“Structured, industry-aligned training helped me secure a role at ZoomInfo. Hands-on, real-world problem-solving strengthened my technical skills and confidence.”
Mohammad Ammar
ZoomInfo
“Key to transitioning without prior experience. Structured mentorship and rigorous training built strong technical confidence, plus valuable career planning.”
Umashankar Pati
RSystems
“Crucial in helping me transition into a technical role. Patient mentorship and guidance in resume building and interview prep were instrumental.”
Ankita Singh
EXL Services
Hiring partners
Where our alumni work
Target
Weekly schedule
Week-by-week curriculum
Five phases, twelve weeks, one continuous build from spreadsheets to a placement-ready portfolio.
Phase 1
Phase 2
Phase 3
Phase 4
Phase 5
- Saturday 10:00 AM – 12:00 PM — Core Session 1
- Saturday 1:30 PM – 3:30 PM — Core Session 2
- Sunday 10:00 AM – 12:00 PM — Core Session 3
1
Phase 1 — Foundations
Weeks 1–2Core content (6 hrs) · Week 1
- Python basics refresher — variables, data types, functions, loops, conditionals
- Working with APIs & SDKs — installing packages, virtual environments
- Environment variables & API key management, JSON handling
- Light OOP introduction — classes & objects, just enough to read/write simple ones
What's covered
- Google Colab setup & intro to the GenAI landscape
Core content (6 hrs) · Week 2
- Core concepts of Generative AI & LLMs — transformers, tokens, embeddings
- How models generate text — capabilities vs. limitations
- Hands-on: calling the OpenAI SDK directly
What's covered
- First guided hands-on AI API call
2
Phase 2 — Core AI Engineering
Weeks 3–7Core content (6 hrs) · Week 3
- Prompt engineering fundamentals — zero-shot & few-shot prompting
- Chain-of-thought prompting, structured outputs
What's covered
- Product design & first working prompts
Core content (6 hrs) · Week 4
- Quick just-in-time OOP refresher (right before it's needed)
- LangChain fundamentals — chains, agents, memory
What's covered
- Add chains & memory
Core content (6 hrs) · Week 5
- Vector database orientation — embeddings explained
- Semantic search fundamentals, building a RAG pipeline
What's covered
- Add retrieval-augmented grounding
Core content (6 hrs) · Week 6
- Agentic AI — the ReAct pattern (reasoning + acting)
- Tool-calling, intro to multi-agent orchestration
What's covered
- Add agent logic & tool-calling
Core content (6 hrs) · Week 7
- Multimodal — image generation & vision-language basics
- Fine-tuning basics — LoRA/PEFT, guided walkthrough
What's covered
- Image feature + fine-tuned component
Capstone project
Product 1 complete — RetailGenie AI, Intelligent Retail Assistant
3
Phase 3 — Applied AI Engineering
Weeks 8–9Core content (6 hrs) · Week 8
- Applying prompt engineering, LangChain & RAG to a new domain
- Semantic search system design
What's covered
- Build core retrieval & search logic
Core content (6 hrs) · Week 9
- Refining search relevance & result quality
- Applying agentic tool-calling where useful
What's covered
- Ship the semantic search system
Capstone project
Product 2 complete — InfoNavigator AI, Smart Search & Navigation System
4
Phase 4 — Evaluation & Deployment
Weeks 10–12Core content (6 hrs) · Week 10
- Applying every learned technique to a document-understanding domain
- Pure implementation — no new topics
What's covered
- Build the document understanding engine
Capstone project
Product 3 complete — DocuMind AI, Intelligent Document Understanding Engine
Core content (6 hrs) · Week 11
- Evaluation & responsible AI — hallucination detection, retrieval quality checks
- LLM-as-judge techniques
- Prompt injection risks, content moderation, data privacy
What's covered
- Evaluate Products 1, 2 & 3
Core content (6 hrs) · Week 12
- Deployment fundamentals — wrapping AI apps with FastAPI/Streamlit
- Taking all 3 products from notebook to live, shareable apps
What's covered
- Deploy all 3 products live
5
Phase 5 — Portfolio & Interview Readiness
Week 13Core content (6 hrs) · Week 13
- Presenting all 3 AI products — portfolio presentation
- Resume & LinkedIn optimization
- Mock interviews (technical + HR rounds)
- Salary negotiation basics
What's covered
- Final portfolio review & mock interviews
Capstone projects
Real-world projects delivered across the program
RAG · Conversational AI
RetailGenie AI — Intelligent Retail Assistant
Conversational product recommendation assistant using LLMs and retrieval-augmented generation to help shoppers find exactly what they need
RAG · Semantic Search
InfoNavigator AI — Smart Search & Navigation System
Semantic search system built with vector databases and embeddings, enabling intelligent, meaning-based information retrieval
LangChain · Document AI
DocuMind AI — Intelligent Document Understanding Engine
A document parsing & understanding pipeline built with LangChain, with responsible AI practices woven in throughout
Toolkit
Tools and platforms you will use
Python
OpenAI
LangChain
HuggingFace
PyTorch
TensorFlow
Scikit-Learn
- RRAG
Google Colab
Get certified
Certificate of Completion
Every learner who completes the program receives a Certificate of Completion from Skillancy.
Practice
Python interview questions for data analysts — practise free
Every Generative AI Program learner gets unlimited access to our in-browser practice sets. Start with these Python and SQL interview questions — no signup, code runs in your browser.
Python interview questions for data analyst
30 problems with hints, tests and explanations
- Clean messy city names from a CRM exportEasy
- Total campaign revenue from prices and quantitiesEasy
- Count orders by payment channelEasy
- Bucket engagement scores into segmentsEasy
- Median salary without using a libraryEasy
- Z-score normalise a spend array with NumPyMedium
FAQ
Frequently asked questions
Ready to start learning?
Create your account, request enrolment and start with the free preview sessions.