Available · India · Remote
Abhijeet Chauhan
Full-Stack Engineer — Backend-leaning · AI & LLM systems
Full-stack engineer with four years of experience, most at home on the backend. I design APIs, services, and data models, deploy them on Google Cloud, and increasingly build with LLMs — agents, RAG, and workflow automation with Langchain. As BauAI's founding engineer I took an AI product from MVP to production and led a small team.
About
I'm a full-stack engineer who leans toward the backend. Most of my work lives on the server side — APIs, data models, microservices, and the infrastructure around them — and over four years I've taken these from first commit to production on Google Cloud.
A lot of that now revolves around LLMs: I build agents, RAG pipelines, and workflow automation with Langchain, then do the unglamorous work of making them dependable in production — clean data models, sensible CI/CD, and monitoring that catches issues early.
Education
Certifications
Recent Projects
An autonomous optimization engine for Meta (Facebook & Instagram) Ads, built for Indian SMBs who don't have the time to babysit their ad accounts.
- Deterministic rule engine that watches campaigns for creative fatigue, weak performance, and budget pacing.
- Daily safety limits with one-click undo on every automated action, plus full action logging.
- Weekly AI-generated performance digests powered by Gemini.
A dashboard for building, configuring, and talking to AI voice support agents — upload a knowledge base, set the prompt and voice, then hold a live voice conversation in the browser.
- Configure agents (system prompt, voice, LLM) grounded on uploaded knowledge bases.
- Real-time, in-browser voice conversations with live transcripts via ElevenLabs Conversational AI.
- Server-side tools for order/ticket lookups and live call transfers.
Selected Work
AI Automation Platform
BauAI · 2026An AI product I built from MVP to production as the founding engineer — LLM agents and workflow automation on a MERN + GCP stack.
- Built and shipped the platform end-to-end on GCP, Supabase, and the MERN stack.
- Designed the LLM-agent and workflow-automation layer with Langchain.
- Owned the infrastructure — CI/CD, databases, and performance tuning.
Scalable Microservices Backend
ReviewDale · 2024–2025Cloud-native microservices on GCP, built to stay available and performant under real traffic.
- Designed, deployed, and maintained microservices on Google Cloud.
- Set up load balancing and monitoring across distributed services.
- Tuned performance and kept availability high under load.
Visitrx — Workplace Management
TeensImage LLP · 2024A workplace-management platform handling employees, assets, and processes — deployed across two companies.
- Led a 3-developer team building the full platform.
- Modeled employees, assets, and operational processes into one system.
- Shipped and deployed the product in two real organizations.
Client Backends (Freelance)
Freelance · 2022–2023Backends and full project setups delivered end-to-end for multiple freelance clients.
- Built secure, maintainable backends tailored to each client.
- Handled hosting, deployment, and getting clients online.
Skills & Tooling
Languages
AI / LLM
Frontend
Backend / Data
Cloud / DevOps
Experience
Founding Full-Stack Engineer
- Built and shipped AI products end-to-end on GCP, Supabase, and the MERN stack — from MVP through to production.
- Led a 4-engineer team, setting technical direction and owning delivery of the core features.
- Ran the infrastructure: cloud setup, CI/CD pipelines, databases, and performance tuning.
Service & DevOps Engineer
- Designed, deployed, and maintained microservices on Google Cloud with load balancing and monitoring.
- Kept distributed, cloud-native services performant and highly available.
Lead Developer
- Led a 3-developer team building a workplace-management platform (employees, assets, processes), deployed at two companies.
Freelance Developer
- Built secure backends for multiple clients and handled hosting and deployment.
Get in touch
Have a backend-heavy or AI/LLM project that needs building? Let's talk.