.png){kind=logo}
Shouhardik Saha
Junior Software Engineer specializing in ML, distributed systems, and LLM applications
Connect with Shouhardik
Shouhardik already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Interned at Zonda where he built an AI-driven semantic search solution over ~280M housing/builder records. Iterated from local LLMs via llama.cpp quantization to a vector-embedding retrieval system, then boosted semantic accuracy with a custom spaCy NER layer and re-ranking, optimizing for latency through precomputation. Collaborated with economics-focused stakeholders to reduce manual document/paperwork time by enabling natural-language search over internal data.
Experience
Education
Key Strengths
- Built and iterated a production semantic search system end-to-end
- Scaled AI retrieval pipeline for very large datasets (~280M records)
- Improved search accuracy by adding custom NER on top of vector retrieval
- Pragmatic model/tool selection (local LLM quantization vs cloud API vs vector search) based on constraints
- Performance optimization via precomputation (embeddings/entities) to reduce query-time latency
- Uses measurable IR evaluation (precision/recall/NDCG) plus A/B testing to validate improvements
- Able to translate AI capabilities into value for non-technical stakeholders (housing/economics users)
Discover more candidates like Shouhardik
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent