.png){kind=logo}
Praveen Nutulapati
Mid-level Generative AI Engineer specializing in LLM fine-tuning, RAG, and agentic systems
Connect with Praveen
Praveen 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 multi-agent RAG system at JPMorgan Chase to automate regulated credit analysis and compliance clause discovery across large internal policy/document libraries. Implemented LangGraph-based supervisor orchestration with structured state management (Azure OpenAI) to support long-running, resumable workflows, plus hybrid retrieval + re-ranking and guardrails for reliability. Strong at evaluation/observability (trace logging, LLM-judge, HITL) and at communicating results to non-technical stakeholders via Power BI embeds and Streamlit prototypes.
Experience
Education
Key Strengths
- Built and deployed production multi-agent RAG system automating internal credit analysis workflows
- Designed hybrid retrieval (vector + BM25) with re-ranking for high-precision compliance use cases
- Solved stateless LLM limitations with structured state management enabling long-running, resumable analyst sessions
- Implemented agent orchestration via LangGraph supervisor pattern with short/long-term memory
- Reliability-focused evaluation: trace-based monitoring plus deterministic/heuristic checks, LLM-judge, and human-in-the-loop
- Optimized model strategy across cost/latency/security, including QLoRA fine-tuning and AWQ quantization for throughput
Discover more candidates like Praveen
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent