Dhruv Arora

About

LLM/RAG practitioner who built an AWS-based enterprise document search and summarization platform with RBAC and scaled it to 10K+ users, solving relevance issues via contextual chunking and hybrid retrieval. Also designed agentic workflows for a telecom forecast-validation use case using sub-agents, tool APIs, and strict context management, and has proven pre-sales influence (supported a $300K manufacturing deal with a roadmap-driven pitch).

Experience

Education

Key Strengths

• Built and scaled an enterprise search + summarization/RAG platform to 10K+ employees
• Improved answer relevance by diagnosing retrieval issues and implementing contextual chunking
• Designed scalable ingestion architecture using async queues and workflow orchestration (SQS + Step Functions)
• Separated ingestion from query path to protect latency; strong performance/scalability engineering
• Implemented query scaling with ECS, load balancer, autoscaling driven by p95 latency and CPU
• Pragmatic caching strategy (LRU) to reduce unnecessary index searches
• Creative solution for user-uploaded docs: local RAG with FAISS stored in Redis with TTL
• Strong agent design for real-world workflows: decomposed forecast validation into sub-agents with targeted tools
• Disciplined approach to LLM reliability: short-horizon task decomposition and context-window-aware API design
• Effective technical communication: demo/workshop structure centered on the 'why' and audience engagement techniques
• Pre-sales impact: helped close a $300K deal by reframing requirements into a broader adoption roadmap