.png){kind=logo}
Tharun Kshathriya Sangaraju
Mid-level AI Engineer specializing in LLM orchestration, RAG, and multi-agent systems
Connect with Tharun
Tharun 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
Research Assistant at the University of Houston who built and live-deployed a production RAG system for 1000+ research documents, using hybrid retrieval (dense+BM25+RRF) with cross-encoder reranking and RAGAS-based evaluation; reported 66% MRR, 0.85+ faithfulness, and 68% lower LLM inference costs. Also built a deployed LangGraph multi-agent research system (Researcher/Critic/Writer) with tool integrations (Tavily, arXiv) and dual memory (ChromaDB + Neo4j), plus freelance automation work delivering a WhatsApp chatbot and n8n workflows for a wholesale clothing business.
Experience
Education
Key Strengths
- Built and deployed production RAG system over 1000+ research documents
- Designed high-precision hybrid retrieval pipeline (dense + BM25 + RRF + cross-encoder reranking)
- Balanced retrieval quality vs latency via candidate pool tuning
- Established post-deployment evaluation/monitoring using RAGAS (faithfulness, answer relevance, context precision)
- Improved outcomes with measurable metrics (66% MRR, 0.85+ faithfulness, 68% reduction in LLM inference costs)
- Implemented iterative production improvements based on real user query behavior (HyDE, chunk-size tuning)
- Built and deployed LangGraph multi-agent research workflow with critic feedback loops
- Integrated structured + vector memory (Neo4j + ChromaDB) while managing state and avoiding data duplication
- Delivered automation for non-technical client (WhatsApp chatbot + n8n) by scoping pain points and showing early wins
Discover more candidates like Tharun
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent