Sai Vivek Reddy Gankidi

About

Built and shipped a production RAG-based enterprise knowledge assistant to replace slow/inaccurate search across millions of documents, using LangChain orchestration with GPT-4/LLaMA and vector databases. Strong focus on production constraints—latency, hallucination control, and cost—using hybrid retrieval, guardrails, LLM-as-judge validation, and model routing, and has experience translating non-technical stakeholder pain points into measurable outcomes.

Experience

Education

Key Strengths

• Built and deployed production RAG knowledge assistant over millions of documents
• Performance optimization for LLM systems (latency reduction via hybrid search, async retrieval, streaming)
• Hallucination mitigation using strict grounding, prompt guardrails, and LLM-as-judge validation
• Cost optimization through token tracking, model routing, caching, and dynamic context limits
• Reliable agent/workflow engineering with modular stages, guardrails, and safe fallbacks
• Systematic evaluation approach (offline datasets, regression tests, recall/relevance metrics)
• Effective collaboration with non-technical stakeholders via measurable goals and iterative demos