Poorna Pedapudi

About

Software engineer focused on data platforms and applied LLM systems: built an internal data quality monitoring layer to catch silent data drift and iterated post-launch after finding ~30% false-positive alerts, reducing noise via dynamic baselines and improved structured logging. Also shipped a production RAG-based internal knowledge assistant over Jira/Confluence with citations, confidence-based fallbacks, and nightly automated evals to prevent regressions.

Experience

Education

Key Strengths

• Owned end-to-end delivery of a data quality monitoring feature (design → launch → iteration)
• Data reliability mindset: schema validation, checkpointing, idempotent writes, and observability
• Metrics-driven iteration (identified ~30% false-positive alerts and reduced noise via dynamic baselines)
• Pragmatic tradeoff decisions (async validation for non-critical datasets to manage latency)
• Production RAG system design with guardrails (citations, confidence thresholds, fallbacks, rule-based filters)
• Established automated LLM evaluation/regression loop with rollback when prompt changes reduced accuracy