Uday Kumar gattu

About

Built and deployed a production LLM/RAG knowledge assistant integrating internal docs, wikis, and ticket histories to reduce tribal-knowledge dependency and repetitive questions. Emphasizes reliability via grounding + a validation layer, and achieved major latency gains (>50%) through vector index optimization, caching, quantization, and selective re-validation. Comfortable orchestrating end-to-end LLM/data workflows with Airflow, Prefect, and Dagster, including monitoring and alerting.

Experience

Education

Key Strengths

• Built and deployed a production RAG system grounded in internal knowledge to reduce repeated questions and speed onboarding
• Strong data quality approach: normalization, removing outdated content, and prioritizing authoritative sources to improve answer stability
• Performance optimization across the full LLM pipeline (faster vector indexes, caching, quantized models, selective re-validation) cutting response time by >50%
• Practical orchestration experience (Airflow/Prefect/Dagster) for reliable ingestion, retries, monitoring, and automated refresh cycles
• Rigorous testing/evaluation methodology with benchmarks, unit + E2E tests, stress tests, and measurable metrics (precision/recall/hallucination rate/latency)
• Effective collaboration with non-technical stakeholders to translate workflows into usable AI assistants and iterate via prototypes