Chandini Sattineni

About

Backend/LLM engineer who ships production internal tooling end-to-end: automated data-request processing with monitoring-driven improvements (better error diagnostics and lower latency via query/index tuning). Also built a RAG-based internal Q&A system over company docs and operational logs with guardrails (similarity thresholds, fallbacks, response limits) and an eval loop using real user queries and human review to drive prompt/retrieval changes.

Experience

Education

Key Strengths

• Owned feature end-to-end (API design through deployment and monitoring)
• Iterates based on user feedback and operational metrics (tickets/Slack + logs/latency)
• Improved developer/user experience via clearer validation errors and structured error codes
• Performance tuning: reduced latency by optimizing queries (indexes, joins, response shaping)
• Shipped production RAG system using embeddings + vector retrieval over internal docs/logs
• Implemented LLM guardrails (similarity thresholds, fallbacks, response length limits) to prevent hallucinations
• Built LLM evaluation loop with real-user test sets, human review, and metric-driven iteration
• Built reliable, observable data pipelines with normalization, retries, and dead-letter handling