Looking for a job

Sumit Kumar

@sumitkumar42

Message

I build production-oriented GenAI, RAG, and data engineering systems.

India

Message

What I'm looking for

I'm seeking a Data Science, Data Engineering, or GenAI role where I can build production-oriented AI/ML systems, RAG pipelines, LLM workflows, vector search, and reliable backend infrastructure.

I've built production-style GenAI systems, including Nyaysethu, a context-aware legal document retrieval assistant using LangChain, Gemini, Hugging Face embeddings, Pinecone, Flask, and MongoDB.

At CodeBasera, I improved a multi-turn conversational AI system to a 90%+ task-completion rate across 50+ test cases and 20+ scenarios. I also built an LLM-driven pipeline that extracted 10+ structured family-data attributes from unstructured conversations.

I build beyond models: my Mini Load Balancer recreates core nginx/HAProxy functionality from raw Python TCP sockets, with round-robin routing, health checks, failover, concurrent request handling, and manual HTTP parsing.

I'm a Computer Science undergraduate seeking Data Science, Data Engineering, and GenAI roles. I ranked 124th of 13,779 participants in the Meta Cup and have solved 300+ DSA problems.

Experience

Work history, roles, and key accomplishments

AI Developer

CodeBasera

Jun 2025 - Oct 2025 (4 months)

Achieved a 90%+ successful task-completion rate on a multi-turn conversational AI system by optimizing prompts and dialogue flows using LangChain. Built an LLM-driven pipeline to extract structured family-data attributes and designed a QA process across 100+ test interactions.

Lang Chain Prompt Engineering Hugging Face RAG Python QA Testing