Abhishikth Meesala

About

At PwC, built and productionized an agentic RAG enterprise search assistant over 6M internal documents (8M embeddings), deployed across AWS and GCP. Drove major retrieval gains (72%→92% precision via BM25+dense hybrid with RRF and cross-encoder re-ranking), reduced hallucinations 30%, achieved <2s latency at 50–60K queries/month, and cut support tickets 30%—boosting adoption to 2,500 users by adding source-cited answers.

Experience

Education

Key Strengths

• Built and deployed an agentic RAG system ingesting 6M documents and generating 8M embeddings
• Improved retrieval precision from 72% to 92% using hybrid search (BM25 + dense) with RRF and cross-encoder re-ranking
• Reduced hallucinations by 30% through retrieval quality improvements
• Scaled production system to 2,500 users and 50–60K queries/month with <2s response times
• Reduced support tickets by 30% by enabling self-serve enterprise knowledge search
• Strong MLOps/production rigor: monitoring, autoscaling, drift detection (MLflow, W&B)
• Data-driven evaluation approach using 10K validation queries with ground-truth answers
• Effective cross-functional collaboration and adoption strategy (phased rollout, weekly demos, incorporated transparency via citations)

Reference Highlights

• Very passionate about his work
• Designed and deployed LLM-based products into production
• Strong end-to-end ownership across the ML pipeline
• Effectively translates complex AI systems into business outcomes
• Actively incorporates stakeholder feedback
• Turns non-technical input into product decisions
• Excellent communication skills
• Explains technical concepts clearly