AI System Design for software engineers to build scalable AI solutions into production.
30+ Enrolled last week
Gaurav Sen
Founder AIEngg
(Ex-Uber, Directi)
Tanishq Singh
AI Engineer, IIT Madras
& University of Birmingham
Trusted by 600+ engineers across US, India and rest of the world
Your instructors are Gaurav Sen and Tanishq Singh.
Theory
Single and Multi-Agent Systems
Context Engineering in Agents
Types of memory in Agents: short and long term
Designing basic evals for Agents
Coding
Build a scalable and performant agentic application.
Theory
Update documents without rebuilding vector indexes
Build background ingestion pipelines and access control
Use scalable search algorithms for improved context
Build scalable input and output guardrails
Coding
Design a scalable RAG application.
Theory
Build evaluation datasets for agent actions and tool calls
Use LLMs as judge and compare with human evals
Automate regression tests for deployment
Test prompt injection and unauthorized tool usage
Coding
Build an automated eval suite for the agent application.
Theory
Build secure APIs and package AI applications
Connect databases and background workers
Automate testing and deployment using CI/CD
Manage containerized AI applications on cloud
Coding
Deploy the agentic application to cloud with secure APIs.
Theory
Track requests across agent actions and MCP
Monitor errors, token usage, and user feedback
Apply caching, rate limits, async execution
Set up alerts to handle system outages
Coding
Add monitoring and performance optimizations to the app.
Theory
Review system architecture and design choices
Validate security, reliability, and production readiness
Failure modes, and cost/performance trade-offs
Evaluate against real-world use-cases
Coding
Present a production grade AI application with a live workflow.
Turns half written product requirements into something a sprint can be planned from, over a hybrid retrieval pipeline with reranking. RAGAS thresholds are wired into the merge gate at 0.90, so a retrieval regression stops the pull request instead of reaching a user.
A linter for Figma handoffs whose guardrails are implemented rather than promised: groundedness and cross-modal hallucination filters run over every output, and a deterministic audit stays the authority over whatever the model says.
Aniket JadhavA household expense agent that sends the model the merchant, the amount and the date, and nothing else. Field minimisation is the whole prompt injection defence, argued from a threat model and checked by a red team eval rather than asserted.
Lavanya MMEngineering Manager at SAPA support agent that turns a novel issue into a plan, has a person approve it, and then compiles what was done into a reusable skill. Six guardrail modules stand in front of it, including card detection that validates with Luhn rather than pattern matching, and the committed evals report their own misses instead of hiding them.
A financial operations agent that decides for itself how far it is allowed to go. A deterministic confidence formula sorts every decision into one of three states, and anything under the bar routes to a person instead of guessing.
Founder AIEngg.dev | Ex-Uber, Directi
Gaurav Sen is a Software Engineer with experience designing and building AI systems at InterviewReady. He has also worked with companies like Docker and NeonDB in explaining how to build reliable AI systems. Gaurav has previously spoken at the University of Houston-Texas, IIT Gandhinagar, and BITS Hyderabad.
AI Engineer | IIT Madras | University of Birmingham
Tanishq is an AI Engineer and Master's graduate from IIT Madras and the University of Birmingham, with production experience across FinTech, HealthTech, and EdTech. He has built end-to-end RAG pipelines and multi-agent systems using tools like LangGraph, CrewAI, and AWS Bedrock, with deep expertise in agent orchestration, context engineering, and memory for agentic systems. His evaluation work spans hallucination detection, prompt injection, and guardrail testing.
Get feedback from Gaurav & industry experts from Meta, Google, Amazon for 6 weeks
Learn the theory, then implement it immediately on production APIs.
Monthly access to industry leaders and alumni from every cohort.
Every session, forever yours.
Share your new skills with your employer or on LinkedIn.
$2,200
$2,500Launch priceCohort Starts On Nov 7, 2026
7-day money-back guarantee
Learn how to reimburse this programThis program is for software engineers, staff engineers, tech leads and engineering managers who want to build scalable, production-grade AI applications. We expect prior coding experience, a basic understanding of software systems, and some exposure to RAG or agentic applications.
No. This cohort starts where a working prototype ends: agent design, retrieval, evals, deployment, observability and scaling. It assumes you have already built or used a basic RAG or agentic application, and it does not teach ML from first principles.
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.
Two: you should be proficient in at least one programming language, and you should have built or worked on a basic RAG or agentic application. Students are expected to code, design and deploy throughout the program.
