Looking for a job

Sunil Sharma

@sunilsharma3

Message

I build production AI systems, from agentic LLM applications to cloud-deployed machine learning platforms.

India

Message

What I'm looking for

I'm looking to build reliable, production-ready AI products where I can own end-to-end delivery, work directly with clients, and solve real business problems with agentic and retrieval-based systems.

I'm building enterprise AI products at Dotsquares for legal-tech, laboratory automation, and e-commerce clients. I own solution architecture, model development, backend services, and production deployment.

Previously at Avkalan.ai, I led end-to-end ML system delivery, from model training and scalable deployment through monitoring in production. I also designed cloud-native infrastructure focused on cost efficiency, auto-scaling, resource optimization, availability, and performance.

I've built agentic and retrieval-augmented systems using LangGraph and LangChain, including multi-provider LLM routing, safety guardrails, vector search, and tenant-level cost governance. My work includes PetroLabel, which automated coal petrography point counts with an 81.9% accurate 20-class classifier, and a legal AI platform with approximately 200 REST endpoints, four LangGraph agent graphs, and Milvus-backed clause recommendations.

I work directly with clients on discovery, feasibility assessment, estimation, and technical documentation to turn business requirements into reliable AI products.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer

Current

Dotsquares

Oct 2025 - Present (11 months)

Owns AI engineering delivery for enterprise clients across legal-tech, laboratory automation, and e-commerce, including solution architecture, model development, backend services, and production deployment. Builds agentic and retrieval-augmented systems on LangGraph and LangChain with multi-provider LLM routing, safety guardrails, and per-tenant cost governance.

LangGraph Lang Chain Agentic AI RAG Backend Development cloud deployment

AI Engineer

Avkalan.ai

Jan 2024 - Oct 2025 (1 year 9 months)

Led end-to-end ML system lifecycle from model training to scalable deployment and robust monitoring. Architected cloud-native infrastructure with a focus on cost-efficiency, auto-scaling, and resource optimization, and integrated LLM APIs, vector databases, and serverless patterns to improve reliability and reduce latency.