Akash Patil

About

Backend/AI engineer at Intuit who built a production AI-powered case assistant for support agents (FastAPI on AWS EKS) combining Postgres case data, OpenSearch retrieval with embedding reranking, and internal LLMs. Improved peak-season reliability by diagnosing P95/P99 timeout spikes and cutting P95 latency from ~800ms to <400ms via composite indexing, keyset pagination, connection pool tuning, and caching, while adding grounded-generation guardrails (evidence packs, confidence thresholds, fallbacks, human-in-the-loop).

Experience

Education

Key Strengths

• Built and shipped an AI-powered case assistant API for customer support agents (FastAPI on AWS EKS) integrating Postgres, OpenSearch retrieval/reranking, and internal LLMs
• Debugged intermittent P95/P99 latency spikes under burst traffic using distributed tracing and DB/query analysis
• Database performance optimization under concurrency (composite indexes, keyset pagination, reduced overfetching, connection pool tuning, caching)
• Designed safe, grounded LLM outputs with citations/evidence packs, confidence indicators, and fallbacks to prevent hallucinations
• Designed multi-step agent-like workflows with structured outputs, confidence-based verification, and controlled retries/escalation logic
• Production Python maintainability practices: layered architecture, strong typing/Pydantic contracts, async IO discipline, pinned dependencies, CI checks, and on-call observability