Anita Bhagashetti

About

Built and productionized a RAG-based semantic search system for video-derived data, focusing on measurable success metrics (p95 latency, reliability, cost/request) and strong observability (prompt versions, retrieved docs, tool calls, token usage). Experienced in diagnosing real-time issues in LLM/agentic workflows and in supporting go-to-market efforts through tailored technical demos, rapid POCs, and post-close onboarding.

Experience

Education

Key Strengths

• Takes LLM prototypes to production by defining clear success metrics (p95 latency, reliability, failure behavior, cost/request)
• Strong LLM observability practices (structured logs/tracing of prompts, retrieved docs, tool calls, latency, token usage)
• Systematic real-time debugging across input, retrieval/tools, and model output layers
• Improves answer quality by optimizing retrieval (chunking, metadata filters) and enforcing grounding in retrieved context
• Controls latency and reliability with caching, timeouts, dependency health checks, rate limits, and fallbacks
• Cost optimization via prompt and token usage tuning
• Uses small evaluation sets and request replay to validate fixes before rollout
• Effective developer-facing demos/workshops focused on end-to-end live workflows (code/config over slides)
• Partners with sales to tailor demos to customer pain points, build quick POCs, and support onboarding for adoption