.png){kind=logo}
Raja Gurugubelli
Mid-level GenAI Engineer specializing in production RAG and LLM fine-tuning
Connect with Raja
Raja 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
LLM engineer who built a production seller-support RAG system at eBay using hybrid retrieval (BM25 + Pinecone vectors) with Cohere reranking, LangGraph orchestration, and citation-grounded answers. Strong focus on reliability: semantic/structure-aware chunking, automated Ragas-based evaluation with nightly regressions, and production observability (LangSmith) plus drift monitoring (Arize). Also implemented a multi-agent fraud pipeline with AutoGen using JSON-schema contracts and explicit termination conditions.
Experience
Education
Key Strengths
- Built and deployed production RAG system for seller support at eBay
- Hybrid retrieval + reranking architecture (BM25 + embeddings + Cohere Rerank) to improve precision
- Deep practical expertise in chunking strategies; implemented semantic + structure-aware chunking with metadata
- Reduced hallucinations via automated evaluation (Ragas) and iterative retrieval/prompting improvements
- Designed reliability process with pre-defined metrics, nightly regression benchmarks, and threshold-based gating
- Production LLM observability and monitoring using LangSmith tracing and Arize drift detection
- Multi-agent workflow design with strict JSON-schema contracts and termination conditions to prevent silent failures/loops
- Effective collaboration with non-technical stakeholders; aligned system behavior to trust and business KPI (ticket volume reduction)
Discover more candidates like Raja
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent