.png){kind=logo}
Santhosh Kumar
Mid-level GenAI/ML Engineer specializing in LLM agents and RAG for Financial Services & Healthcare
Connect with Santhosh
Santhosh 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
Built and deployed a production GenAI internal support agent at Bank of America (“Ask GPS/AskGPT”) using RAG on Azure, focused on reducing escalations and improving response quality for repetitive knowledge-based queries. Demonstrates strong production LLM engineering: custom LangChain orchestration, retrieval tuning to reduce hallucinations, rigorous offline/online evaluation, and model benchmarking with dynamic routing (e.g., GPT-4 vs Claude).
Experience
Education
Key Strengths
- Built and deployed an internal enterprise GenAI support agent (RAG) on Azure for high-volume knowledge queries
- Strong hallucination control via retrieval improvements (chunking, metadata filters, relevance thresholds) and prompt redesign (citations, 'I don’t know' behavior)
- Production-grade LangChain orchestration with custom retrievers and lightweight custom chains (conditional routing, fallbacks, confidence checks)
- Lifecycle evaluation mindset: separates retrieval vs generation evaluation; uses offline datasets plus production observability (latency, tokens, errors, fallback frequency)
- Evidence-driven model selection and benchmarking (evaluated GPT-4 vs Claude; implemented dynamic model routing by query complexity)
- Effective collaboration with non-technical ops/product stakeholders using outcome-based framing and iterative demos/prototypes
Discover more candidates like Santhosh
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent