upgrad-logo
IIT/IIM Courses

POPULAR

IIT Kharagpur - Executive Post Graduate Certificate in AI-Native Software Engineering

A production-first, AI-native engineering programme for Software Engineers to transition from traditional architecture to building intelligent, AI-powered systems. Combines full-stack engineering with modern AI.

banner image

IIT Kharagpur: Legacy That Nurtures Excellence

India’s First IIT

Established in 1951, IIT Kharagpur is India’s oldest Indian Institute of Technology. For over seven decades, it has shaped engineers and researchers who lead innovation across industry, academia, and technology worldwide.

National and Global Standing

Ranked 5th in Engineering by NIRF 2025, IIT Kharagpur consistently ranked among Asia’s top universities by QS Asia Rankings.

Research That Drives Real-World Impact

Known for high-impact research and strong global citation performance, IIT Kharagpur plays a defining role in advancing areas such as artificial intelligence, computing, and emerging technologies.

image

From Full Stack to AI-Native Systems, led by IIT Kharagpur’s Computer Science & Engineering Department

Slide 1 of 1

100% Live Online, Faculty-Led Sessions

Taught by Professors from IIT Kharagpur CSE Dept.

A Production First Programme

Frontend → Backend → AI Systems → Agents → Production

One Integrated System + Capstone Project

Executive Alumni Status & Award Ceremony

Certification: IIT Kharagpur

A Credential That Carries Weight

Recognised Academic Credential

Earn an Executive Post Graduate Certificate from IIT Kharagpur.

Certificate with Distinction

The top 10 percentile performers in each cohort receive a Certificate with Distinction, formally recognised on the credential.

Academic Credibility with Industry Relevance

An IIT-issued credential that signals rigorous training and readiness for advanced AI roles.

image

The Curriculum for Engineers Who Own the AI Layer. Design Systems, Build with AI, Ship to Production

100%

Faculty Led

One

System

Production

Grade AI

Build One AI System. End-to-End. - Not demos. One real production system. Frontend → Backend → RAG → Agents → Deployment

Vibe Coding with Engineering Judgment -Don’t just use AI, learn when to trust it. Build manually → rebuild with AI → audit outputs for bugs, security gaps, and architecture trade-offs.

MCP Protocol & Agentic Engineering - Go beyond chatbots to real AI systems. Build MCP servers, multi-agent workflows, and integrate with real-world services (WhatsApp, APIs, etc.).

India-Specific from Day One - Built for real-world Indian use cases. OCR for PAN /GST /Aadhaar, multilingual RAG, INR cost modeling, WA & UPI integrations, DPDP compliance.

AI Security & DPDP Compliance (As Code) - Ship AI systems that are safe and compliant. Prompt injection defense, adversarial testing, and full DPDP implementation (consent, erasure, audit trails).

Evaluation as Engineering Practice - Measure AI quality like you measure code. RAGAS metrics, LLM-as-judge, CI-integrated evaluation gates, and regression testing for AI systems.

imagesrc

The Complete Curriculum

A Structured Path to AI-Native Program

AI-Native Foundations Bridge

Topics covered

Language readiness: Python or TypeScript/React, based on your background. Assessment-driven.

Shared foundations: Docker, REST APIs, and SQL. Assigned to gaps only.

Integration checkpoint: Build a working full-stack mini-system in 2 hours. Mandatory for all.

Building AI-Native Interfaces, Vibe Coding & Real-Time Systems

Module 1

Topics covered

Evaluate foundation models (Claude, GPT-4o, Gemini, Llama, DeepSeek) using cost, capability, and risk

Build Next.js App Router with Server/Client Components, streaming SSR, TypeScript strict mode

Implement WCAG 2.1 AA accessibility with axe-core testing

Build real-time LLM streaming with Vercel AI SDK, loading states, confidence indicators

Deploy on Vercel with 80%+ test coverage and CI/CD via GitHub Actions

Production-Grade LLM Infrastructure

Module 2

Topics covered

Design FastAPI backend with Pydantic v2 typed validation and RFC 7807 error handling

Integrate OpenAI and Anthropic SDKs with streaming, structured outputs, prompt versioning

Build resilient AI services: circuit breakers, fallback chains, timeout management

Process Indian documents: PAN, GST invoices, Aadhaar via vision models + OCR

Instrument per-request cost attribution, user-level spend alerts, async processing

Retrieval, Context Engineering & Evaluation

Module 3

Topics covered

Build a complete RAG pipeline from scratch with only SDKs and HTTP calls

Design an abstraction layer resilient to LangChain/LlamaIndex version churn

Implement multi-tenant retrieval with pgvector, row-level security

Add multilingual retrieval via Bhashini, with fallback to open-source embedding models where API coverage is incomplete

Evaluate with RAGAS (faithfulness, relevancy, precision, recall) + CI regression gates

Agentic Engineering & Protocol Design

Module 4

Topics covered

Design the perceive-reason-act-observe loop; React and plan-and-execute patterns

Build stateful agents with LangGraph: state machines, tool contracts, checkpointing

Build an MCP server with authentication, least-privilege permissions, audit logging

Design prompt-injection-aware tools; survey emerging A2A and browser-use patterns

Implement human approval gates (>₹1K), escalation workflows, multi-agent coordination

Integrate WhatsApp Business API, UPI, GST validation, DigiLocker

Skills acquired

AI Systems Reliability, Security & Governance

Module 5

Topics covered

Langfuse: alerting, SLA dashboards, cost anomaly detection

Semantic caching with Redis (40-60% savings)

Intelligent model routing + budget enforcement

CI/CD evaluation gates blocking regressions

Semantic prompt versioning + model-version tracking

Zero-downtime deployment of complete system

OWASP LLM Top 10 + Promptfoo red-teaming (30+ tests)

DPDP Act 2023 as code: consent, erasure, minimisation

Incident response: rollback, post-mortem methodology

The Proof

Capstone

Topics covered

Define & Architect: Translate a business problem into full-stack engineering scope: frontend, backend, AI layer, RAG pipelines, and deployment architecture.

Build & Evaluate: Develop using AI-assisted engineering, integrating LLMs and full-stack components, then test for performance, accuracy, cost, and reliability.

Deploy & Own: Ship with APIs, monitoring, and governance in place, and graduate with a live AI-native system that demonstrates real engineering ownership.

The tools reshaping business. Understand the landscape. Direct the choices.

Claude

Bhashini

Anthropic

LangChain

OpenAI

AgentGPT

Locust

FastAPI

Redis

LlamaIndex

WhatsApp API

Docker Compose

Langfuse

TypeScript

nxt

Promptfoo

Jest

pgvector

MCP Protocol

Docker

Cursor AI

GitHub Actions

RAGAS

Faculty

Experts Shaping the Academic Direction

6

India’s Strongest Academic Bench in AI & Computer Science

Slide 1 of 6
image

Prof. Niloy Ganguly

Professor & Head, Dept. of CSE

image

Research Areas: Artificial Intelligence and Machine Learning, Complex and Social Networks, Data and Web Mining, Natural Language Processing

University Profile
image

Prof. Soumya K. Ghosh

Professor, Dept. Of CSE

image

Research Areas Spatial Informatics, Spatial Webservices, Cloud Computing, Spatio-Temporal Data Analysis

University Profile
image

Prof. Sandip Chakraborty

Associate Professor, Dept. Of CSE

image

Research Areas: Computer Networks, Human Computer Interaction, Pervasive and Ubiquitous Computing, Computer Systems

University Profile
image

Prof. Bivas Mitra

Associate Professor, Dept. Of CSE

image

Research Areas: Network science, Multilayer networks, Social networks, Data science, Anomaly detection, Mobile affective computing, Socio-mobile applications, Social-IoT

University Profile
image

Prof. Jibesh Patra

Asst. Professor, Dept. Of CSE

image

Research Areas: Software Engineering, Artificial Intelligence, System Security

University Profile
image

Prof. Mainack Mondal

Asst. Professor, Dept. Of CSE

image

Research Areas: Hardware Security & Verification, Human-Centered AI & Community Feedback, AI Safety & Misinformation, Privacy & Data Governance

University Profile

Systems You Will Build & Ship

Portfolio of real AI systems you can demonstrate, explain, and extend

Slide 1 of 6
3-d3b4b949883240dc9ac6244579d62b8a.png

AI-Native Commerce Dashboard

Operator dashboard for a live D2C workflow. AI generates listings, pricing, and SEO in real time. WCAG-compliant, OAuth-secured, CI/CD-enabled.

4 (2)-f4e224c7150148d5afd0e48034783fcd.webp

Production-Grade AI Backend Infrastructure

FastAPI backend routing requests across LLMs by cost, latency, and complexity. Circuit breakers, failover, and tenant-level cost tracking.

6-566fd69728f944168528a35d6ce8d058.png

Enterprise Knowledge & Reasoning System

Multi-hop RAG on real commerce data. Vector, hybrid, and graph-aware retrieval. Multilingual pipelines with RAGAS evaluation and CI gates.

2 (1)-934823ae68c740feaf7886719179cc7f.webp

Autonomous AI Operations Agent

Resolves queries & automates workflows with human-in-loop controls. LangGraph & MCP with prompt-injection defenses & audit trails.

5-f8eb01218cda468bb4432490d1c2a8c1.png

Production Hardening, Reliability & Governance

Peak traffic simulation, intelligent model routing, and cost monitoring. Adversarial testing and DPDP compliance built in.

4-2ceb1a1e6e7a4cd3885d62816836f4af.png

GitHub Portfolio

Clean repo with CI/CD, eval gates, semantic prompt versioning, comprehensive README

Capstone: Build One System. Ship to Production

Your Signature AI-Native System Designed, Built, and Shipped by You

Integrated

AI System

AI-Native

Architecture

Production

Deployment

Define - Select a business problem and translate it into a system with clear product and engineering scope.

Architect -Design the end-to-end system-frontend, backend, AI layer, RAG pipelines, agents, and deployment architecture.

Build - Develop the system using AI-assisted engineering, integrating LLMs, workflows, and full-stack components.

Evaluate - Test for performance, accuracy, cost, and reliability, including AI evaluation and system behaviour.

Deploy - Ship a production-ready system with APIs, monitoring, observability, and governance in place.

imagesrc

Graduation Ceremony: Culmination at the IIT Kharagpur Campus

1

Award Ceremony

Certificate conferred by IIT Kharagpur leadership

Interact with the professors who taught you

On-campus academic recognition with your cohort

Experience the legacy of India’s first IIT

Disclaimer: Images are indicative and for illustrative purposes only

image

IIT Kharagpur marks 75 years of shaping India’s engineering and technology leadership

As India’s first IIT, the institute’s Platinum Jubilee celebrates seven and a half decades of academic rigour, research excellence, and nation-building impact. This milestone reflects IIT Kharagpur’s enduring legacy of producing world-class engineers, researchers, and innovators who continue to influence industry, academia, and society globally.

video thumbnail image
play

How will upGrad support you?

    Language readiness: Python or TypeScript/React, based on your background. Assessment-driven.

    Shared foundations: Docker, REST APIs, and SQL. Assigned to gaps only.

    Integration checkpoint: Build a working full-stack mini-system in 2 hours. Mandatory for all.

EPGC in AI-Native Software Engineering

How To Apply

Complete your application and enrol in the program with three easy steps!

Eligibility

Graduation with a minimum of 50% marks. B.Tech/ M. Tech, B.E/M.E (CS, IT, AI, ECE preferred), B.Sc/M.Sc (CS/Mathematics/Statistics), MCA/BCA. Candidates from other disciplines must have a minimum of 2 years of experience in the technology field.  Pre-requisite: 2+ years professional software development Python or JavaScript/Type Script proficiency

Slide 1 of 3
image-Complete Application

Complete Application

Fill out an application giving your basic profile details.

arrow-image
image-Get Shortlisted

Offer Letter & Reserve Seat

Receive an offer letter and pay INR 10,000 to reserve a seat.

arrow-image
image-Complete Payment

Payment

The remaining balance is to be closed within 7 days or the batch start date, whichever is sooner.

EPGC in AI-Native Course Fee

8 Months
Starting at
INR 6,031/month
Totally INR 1,77,000*

Reserve your seat

Pay INR 10,000/- to block your seat
View Plans
fee image

upGrad Learner Support

Talk to our experts. We are available 7 days a week, 10 AM to 7 PM

text

Indian Nationals

text

Foreign Nationals

Disclaimer

  1. The above statistics depend on various factors and individual results may vary. Past performance is no guarantee of future results.

  2. The student assumes full responsibility for all expenses associated with visas, travel, & related costs. upGrad does not .