Leela Tikkisetty

About

Software engineer with experience at Google and the City and County of San Francisco building production AI systems, including a RAG-based internal support chatbot and ML-driven ticket priority tagging. Has scaled data/ML platforms with Airflow on GCP (1M+ records/day, 99.9% SLA) and deployed multi-component systems with Docker and Kubernetes (GKE), using modern LLM tooling (LangChain/CrewAI, Claude/OpenAI, Pinecone/ChromaDB, Bedrock/Ollama).

Experience

Education

Key Strengths

• Built and deployed a production RAG chatbot to improve internal ticket resolution using 100+ policy documents
• Designed high-reliability Airflow ETL pipelines on GCP processing 1M+ ad records/day with 99.9% SLA uptime
• Containerized and deployed 15+ ML/ETL platform components using Docker and GKE
• Strong approach to reducing hallucinations via RAG grounded in verified internal data and vector stores
• Cross-functional delivery with non-technical stakeholders; iterated POC to production for automated ticket priority tagging
• Owned end-to-end production delivery (frontend/backend/data/infra) for municipal ticket triage agentic system
• Designed multi-agent orchestration over 100+ municipal datasets using LangGraph + MCP
• Reduced manual ticket routing by 40% and improved resolution accuracy for complex queries by 25%
• Achieved sub-200ms latency and maintained 99.9% uptime via custom health checks/probes
• Productionized secure RAG with automated hallucination checks and grounding for public-facing responses
• Modernized legacy system using strangler-fig approach with fallbacks and parallel-run testing
• Built automated ETL/ELT pipelines reducing manual data entry by 80%
• Delivered production solution in weeks while embedded with minimal oversight; processed 2TB+ daily data (Dataflow/BigQuery)
• Partnered with C-suite stakeholders to translate ambiguous goals into roadmap; weekly demos and sprint planning leadership