Omkarnath THAKUR

About

Internship project at Builder Market: built an end-to-end production multimodal LLM application that estimates renovation/replacement costs from appliance photos (CLIP embeddings) or text descriptions, combining fine-tuning with agentic RAG. Focused heavily on real-world performance constraints—latency and cost—using parallel agent workflows, model routing to smaller/open-source models, re-ranking, and retrieval chunking, and collaborated closely with CEO/co-founders to deliver the solution.

Experience

Education

Key Strengths

• Built and deployed an end-to-end multimodal LLM system (backend, frontend, production LLM calls)
• Applied multiple latency-reduction strategies (model routing, parallel agent design, re-ranking, chunking)
• Hands-on with agentic RAG/chatbot architectures and evaluation approaches (LLM-as-judge, cost-focused evaluation)
• Strong MLOps/orchestration exposure (LangGraph, CI/CD with GitHub Actions/Jenkins, Kubernetes)
• Structured approach to model/method selection via data curation, prototyping, and baseline comparisons