Open to opportunities

Nikhil Chouhan

@nikhilchouhan1622

Message

AI Engineer shipping production LLMs and agents for fintech, end-to-end.

India

Message

What I'm looking for

I want to build AI-native fintech products where I can own production LLM/agent systems end-to-end—RAG, multi-provider reliability, and evaluation—while optimizing latency, cost, and uptime with solid engineering practices.

I’m an AI Engineer with 3+ years shipping production LLM and agentic systems end to end for financial services (BFSI and fintech). As a Founding AI Engineer at Cognifin Labs, I own production AI features, from model integration and provider routing to evaluation, latency, and cost using FastAPI microservices on AWS. I focus on depth in RAG over financial documents, multi-agent orchestration (LangGraph), and classical ML for ranking and recommendation.

I’ve built an LLM function-calling and structured-output layer (with schema validation) for spend categorization, anomaly flagging, and conversational nudges, backed by LiteLLM provider fallback and guardrails for reliable, auditable responses. At Digital Business Technology, I shipped multi-tenant LLM and RAG workflows into user-facing SaaS products and deployed and operated 8+ AWS applications with Docker and blue-green CI/CD, reducing infrastructure cost 30% with zero-downtime releases. I also work across classical ML and full-stack React, and I'm IEEE-published in ML.

Experience

Work history, roles, and key accomplishments

Current

Founding AI Engineer

Current

Cognifin Labs Private Ltd

Jan 2026 - Present (5 months)

Founding AI engineer owning production AI end to end on FastAPI and AWS for an AI-native fintech platform. Built an LLM function-calling and structured-output layer (Gemini 3.5 Flash) for spend categorization, anomaly flagging, and nudges, with LiteLLM routing and fallback, plus a recommendation engine using spend-pattern clustering and offer-ranking across 200+ partner brands.

LLM RAG LangGraph LiteLLM Generative AI Anomaly Detection AWS Cost Anomaly Detection Prompt Engineering fastAPI Python PostgreSQL AWS Recommendation Systems Langchain Agents Python 3

Software Engineer (SDE-1)

Digital Business Technology

Jul 2023 - Nov 2025 (2 years 4 months)

Built LLM and RAG capabilities for a multi-tenant BFSI SaaS, including knowledge-base pipelines (chunking, embeddings, retrieval tuning) and function-calling workflows driving user-facing automation. Deployed and operated 8+ AWS applications with Docker and blue-green CI/CD, cutting infrastructure cost by 30% with zero-downtime releases.

fastAPI NestJS PostgreSQL Docker Performance Tuning

Full Stack Developer Intern

Infosoft Systems

May 2022 - Nov 2022 (6 months)

Built and maintained REST APIs using NestJS, debugging production issues to improve backend response times by 40%. Owned CI/CD deployments on Ubuntu and supported delivery and reliability improvements across backend services.

NestJS REST APIs CI CD Performance Optimization PostgreSQL

Frontend Developer Intern

CartGeek

Dec 2020 - May 2021 (5 months)

Built component-driven React UIs and integrated REST APIs to support product features. Led a team of 5 interns on code reviews and delivery to accelerate frontend execution and quality.

React REST APIs Code Review Team Collaboration TypeScript

Education

Degrees, certifications, and relevant coursework

NMIMS MPSTME

Bachelor of Technology, Computer Engineering

Grade: GPA 3.34/4.0

Activities and societies: Project Head, IEEE MPSTME Student Branch (2021); 3rd Place, Polarizer Innovation Competition; Publications: Edit Any Face (IEEE INCOFT 2022) and vRecruit (IEEE ICITIIT 2022).

B.Tech in Computer Engineering at NMIMS MPSTME, completed in 2023 with a GPA of 3.34/4.0. Served as Project Head for the IEEE MPSTME Student Branch and published papers including work in IEEE INCOFT 2022 and IEEE ICITIIT 2022.