Advanced Certificate in AI Forward Deployed Engineering (Batch 2)
Features
Programme Overview
The AI Forward Deployed Engineering Programme from IIT Delhi is designed for working engineers and technologists looking to build the skills that AI companies pay a premium for: deploying AI into real customer environments, making it work with real data, real users, and real enterprise constraints.
Led by the Head of the Bharti School of Telecommunication Technology and Management, IIT Delhi alongside leading faculty from across the IIT Delhi and subject-matter experts drawn from active FDE practice. The programme is structured around a 70/30 build-to-deliver split, combining deep engineering work with the client-facing delivery skills that separate a working prototype from a production-grade deployment.
Across the programme, participants will learn to design and ship production RAG pipelines, build and debug agentic AI systems, fine-tune and customize large language models, harden AI deployments for regulated industries under HIPAA, DPDP, and EU AI Act requirements, and communicate outcomes confidently to executive stakeholders. With five shipped capstone projects including a portfolio-grade final deployment defended live to a subject-matter expert panel. The programme equips learners to step into Forward Deployed Engineer, Applied AI Engineer, and AI Solutions Architect roles at the organizations building the next generation of enterprise AI.
₹ 1,80,000 + 18 % GST
Class Schedule
Weekend Classes
Eligibility Criteria
Graduation in any of these disciplines: B.Tech/BE; BCA/MCA; B.Sc in all streams; BA/MA in mathematics.
Coding experience, in any language: Coding day to day in Python, Java, C#, JavaScript or another language? You’re well placed. Python is used throughout the programme. If it’s new to you, a strong grasp of its basics before starting makes the transition smoother.
Hands-on with the cloud and GitHub: Deployed an app, or explored cloud platforms such as AWS, Azure or GCP? That's a useful head start. Used GitHub to save and share code? Even better. If either is new to you, knowing the basics is important before the programme starts, though these aren't formal barriers to entry.
Programme Highlights
One Of India's First FDE Programmes
Taught By IIT Delhi Faculty; Industry SMEs Drive Sessions
Optional 2 -day Campus Immersion At IIT Delhi
QInsights No-Code Lab Access For Every Learner
70 /30 Build-to-deliver Split Across The Curriculum
Mini-capstones At Every Phase; Portfolio-grade Final Project
E-certificate From CEP, IIT Delhi On Completion
Security, Compliance, And Regulated-industry Deployment Covered
Weekend Format Designed For Working Professionals
145 Hours Of Live And Recorded Learning
Programme Modules
BUILD – AI Foundations for FDEs
Frontier and open-weights models, how they work at FDE level, and the FDE mental model: AI in a customer environment vs a demo.
BUILD – Evaluation Foundations
Golden datasets, test cases and release gates, so every change is proven to make the tool better.
BUILD – Python & Production Engineering
A Python bootcamp, then APIs, service contracts, testing, Git and containers, through to your first LLM call. The habits that make code shippable.
BUILD – Prompting & LLM Control
Prompt design, structured outputs and prompt-as-code, with model choice made on evidence across frontier models.
DELIVER – Discovery & Problem Framing
Run discovery, map stakeholders (CTO, CISO, business owner) and turn a business problem into a scoped, buildable brief.
MINI-CAPSTONE 1 | WEEK 4
Ship your first working AI tool. Containerised, tested and documented like an FDE in a clean one-pager.
BUILD – RAG Architecture I
Ingesting messy enterprise documents, chunking, embeddings, vector databases and hybrid search.
BUILD – RAG Architecture II
Query rewriting, re-ranking, citation handling and secure multi-tenant retrieval.
BUILD – Agentic Systems
Tool calling and agent loops from first principles, then orchestration frameworks, MCP and agent debugging.
BUILD – LLM Evaluation & Observability
Automated RAG evaluation, tracing, regression gates and red-teaming, so quality is measured, not assumed.
DELIVER – Rapid Prototyping for Customers
Visual-first prototyping to win early customer buy-in, and a clear sense of where code takes over.
MINI-CAPSTONE 2 | WEEK 10
Build and defend RAG on messy enterprise docs. Evaluation evidence + architecture write-up.
BUILD – Fine-Tuning & Customisation
When to fine-tune vs prompt vs RAG, a guided customisation run, evaluation gates and cost-benefit math.
BUILD – Deploying AI in Production
From pilot to production on managed cloud platforms: configuration, auth, rollback, serving and latency.
BUILD – Cost, Latency & Scale
Token economics, caching, model routing and load testing. What turns an unprofitable demo into a profitable product.
BUILD – Enterprise Integration
Enterprise data, permissions, lineage and audit trails, with compliance for on-prem and VPC deployments.
BUILD – Security & Responsible AI
LLM threats and defences, PII, hallucination handling, bias audits and regulatory obligations.
DELIVER – Solution Design & Delivery
PRDs and solution design, trade-off communication, scope changes and running war rooms during incidents.
MINI-CAPSTONE 3 | WEEK 15
Rebuild a generic demo for a bank or hospital.
Architecture + prototype + risk register.
MINI-CAPSTONE 4 | WEEK 17
Audit a live LLM app end-to-end.
Audit report + remediation playbook + governance plan.
BUILD – Vertical Playbooks
Deep dives into named domains. Fraud detection, ticket routing, multilingual workflows, clinical-grade healthcare RAG.
BUILD – AI Product Sense
Spotting patterns across deployments. When to build vs configure vs raise to product. The "eyes and ears in the field".
DELIVER – Outcome Communication & Demo Craft
Demoing to a Fortune-500 CTO. Deployment docs customers actually use. Presenting outcomes, not features. Portfolio storytelling.
FINAL CAPSTONE | WEEKS 21–24
Choose your track. Build the prototype. Harden it. Demo it – defended live to an SME panel.
See the principles, then build them
As an add-on learning tool, every learner gets access to the QInsights Lab, where core ideas are taught visually first, with minimal setup, before you build them in code.
QInsights – Visual Learning Lab
Visual-first learning
Minimal setup
Add-on to live classes
Python
OpenAI & Claude APIs
LangGraph
LangSmith
Pinecone
Weaviate
Docker
Kubernetes
Cloud tools
CI / CD pipelines
Eval frameworks
SQL & vector DBs
QInsights Lab Sandbox
Learning Outcomes
Ship RAG, agents and automation that survive messy data, real users and constraints.
Deploy cloud infra, vector databases, serving frameworks and MLOps pipelines end to end yourself.
Connect AI to CRMs, ERPs and APIs with audit trails and SOC2, HIPAA, DPDP compliance.
Defend against prompt injection and hallucinations, protect PII, and audit bias per EU AI Act.
Run discovery, separate pilots from production, and align CTOs, CISOs and business leaders.
Demo to SME panels, train teams, measure ROI, and sell business outcomes not features.
Tools
Python
AWS
Docker
Azure
GCP
Kubernetes
Lang Graph
Lang Smith
Open AI
Pinecone
Weaviate
SQL
Programme Coordinator

Professor Gokulnath Thandavarayan
Assistant Professor
Centre for Automotive Research and Tribology (CART)
Indian Institute of Technology Delhi
Ph.D. (Cum Laude), Miguel Hernández University, Spain.
Research Areas
V2X communications
Connected and automated vehicles
Intelligent transportation systems
5G/6G wireless communications
Industry Collaborations
Bosch · Hyundai · Toyota
Contributor to ETSI standards for CAVs and 3GPP discussions.
Note from the Programme Coordinator
“My work on connected and automated vehicles has taught me one thing: a system is only as good as its performance in the real world. With partners like Bosch, Hyundai and Toyota, the hard part was never the model in the lab. It was making it work reliably in the field, with real data, real constraints and real people depending on it.
AI is now at that same point. Enterprises do not need more demos. They need engineers who can take ideas from prototype to production, integrate them with existing systems and stand behind the results. This programme is built to develop those engineers, with strong applied depth and hands-on deployment work at every stage.”
Programme Sample Certificate


On completion, participants receive a certificate from the Continuing Education Programme (CEP), IIT Delhi.
Two certificate types are issued, based on attendance and assessment performance.
Two Certificate Types
Type 01 – Certificate of Successful Completion
Eligibility:
Candidates who score at least 50% marks overall and have a minimum attendance of 50% will receive a ‘Certificate of Successful Completion’ from CEP, IIT Delhi.
Type 02 – Certificate of Participation
Eligibility:
Candidates who score less than 50% marks overall and have a minimum attendance of 50% will receive a ‘Certificate of Participation’ from CEP, IIT Delhi.
Format & What Is On It
Issued by:
Continuing Education Programme (CEP), Indian Institute of Technology Delhi.
Format:
Verifiable e-certificate only. No printed copy is issued.
Installment Schedule
Programme Fee INR 1,80,000 + 18% GST
Instalment | Date | Amount (₹)** |
Application Fee | Application Fee | 1,000 + 18 % GST |
1st Instalment | Within 4 days of the release of an offer letter | 30,000 + 18 % GST |
2nd Instalment | 5th February, 2027 | 1,50,000 + 18 % GST |
Note:
*GST @ 18% will be charged extra in addition to the fees
The application fee of INR 1,000/- + 18% GST is non-refundable and non-transferable. This fee is in addition to the programme fee and will not be adjusted against the total programme fee.
Refund Policy
Candidates can withdraw within 15 days from the programme start date. 80% of the total fee received is refunded. The applicable tax amount paid is not refunded.
Candidates withdrawing after 15 days from the start of the programme session are not eligible for any refund.
To withdraw, email cepaccounts@admin.iitd.ac.in and refunds_varsity_iitd@interviewbit.com. Refunds, if applicable, are processed within 30 working days.
Frequently asked questions
An Advanced Certificate offered by the Continuing Education Programme (CEP), IIT Delhi, one of India's first FDE programmes, built to take you from prototype to production AI.
Graduates with a B.Tech or BE in any engineering discipline, a BCA or MCA, a B.Sc in any stream, or a BA or MA in Mathematics or a related quantitative field. Coding experience in any language is needed for a quick ramp-up, and Python is used throughout. Hands-on experience with the cloud and GitHub is a useful head start. The programme is built for students and working professionals alike, and no prior AI experience is needed.
76 hours of live online weekend lectures, Q&A and faculty-led discussion; 38 hours of self-paced replays and structured reading; and 31 hours of capstone and lab work, including build sprints, simulations and reviews. Live sessions may be held on Saturday or Sunday, so plan to be available on both days.
Five portfolio builds: a first working AI tool (Week 4), production-grade RAG on messy enterprise documents (Week 10), a regulated rebuild for a bank or hospital (Week 15), a security audit of a live LLM app (Week 17), and a final FDE deployment in one of six industry tracks, defended live to a subject-matter-expert panel (Weeks 21–24). Capstone topics and tools are indicative, and the Programme Faculty may update them.
An add-on learning tool. Every learner gets access to the QInsights Lab, where core ideas are taught visually first, with minimal setup, before you build them in code. It runs alongside the live classes.
The fee is ₹1,80,000 plus 18% GST. You pay a ₹1,000 + GST application fee, then Instalment 1 of ₹30,000 + GST within 4 days of your offer, and Instalment 2 of ₹1,50,000 + GST by 5 February 2027, in one shot or as EMI through NBFC partners.
Withdraw within 15 days and 80% of the fee is refunded, excluding tax. After 15 days there is no refund. Refunds are processed in 30 working days; email cepaccounts@admin.iitd.ac.in and refunds_varsity_iitd@interviewbit.com. The application fee is non-refundable.
A verifiable e-certificate from CEP, IIT Delhi; no printed copy is issued. With at least 50% marks overall and 50% attendance, you receive a Certificate of Successful Completion. With 50% attendance and under 50% marks, you receive a Certificate of Participation.
CEP, IIT Delhi does not provide placement assistance or alumni status. Interviewbit (Varsity) runs a separate role-readiness layer with AI mock interviews, resume reviews and a curated job digest from its hiring partners.
The Continuing Education Programme (CEP) is the only statutory body for offering certificate programmes and issuing certificates at IIT Delhi. It runs online certificate programmes under eVIDYA@IITD for Indian and international participants. For more details, visit cepqip.iitd.ac.in.