Open to opportunities

sachin jat

@sachinjat

Message

I build production AI retrieval systems and scalable event-driven backend platforms.

India

Message

What I'm looking for

I'm open to remote or hybrid roles where I can build production AI retrieval, LLM, and scalable backend systems end to end.

At ATMECS Technologies, I build AI document intelligence and conversational platforms, including hybrid RAG retrieval with Milvus, BGE-M3, BM25, cross-encoder reranking, Docling parsing, and self-hosted Qwen3 inference through vLLM.

I've delivered LLM chat, voice, streaming, function-calling, and multi-tenant microservices for Lemmata, plus AI-powered eCommerce and order-management services for Ordrio. My work spans Kafka, Redis, WebSockets, AWS, Azure, Stripe, Chargebee, SharePoint, and Qlik Cloud.

Previously, I built high-throughput Node.js and NestJS services for Sunfocus Solutions and backend APIs for gaming, eCommerce, matchmaking, and on-demand platforms at Virtoustack. I enjoy owning systems end to end, from design and implementation through debugging, production support, and performance optimisation.

Experience

Work history, roles, and key accomplishments

Current

Senior Backend / AI Engineer

Current

ATMECS Technologies (Sutherland Global Services)

Feb 2024 - Present (2 years 6 months)

Designed and built hybrid RAG retrieval pipelines, document parsing, and self-hosted LLM inference for AI platforms. Developed microservices, event-driven architectures, and integrations for eCommerce and analytics.