Swapnil Ramanna

About

Built a LangGraph-based, tool-routing LLM chatbot to deliver fast, trustworthy investment-stock insights (including tariff impact) and deployed it to production on Snowflake after initially developing in Azure with AI Search and the Microsoft Agent Framework. Improved routing robustness by moving from LLM-based decisions to a deterministic router backed by schema-relationship graphs and YAML metadata, and ran the project iteratively with non-technical stakeholders over an 8-month engagement.

Experience

Education

Key Strengths

• Built and deployed a production LLM chatbot for investment-stock insights using RAG + Text-to-SQL
• Successfully migrated an agent system from Azure to Snowflake despite platform capability gaps
• Improved reliability by replacing brittle LLM-based routing with deterministic routing using schema graphs + YAML metadata
• Strong end-to-end agent/workflow design mindset (data types, chunking, embeddings, retrieval strategy, metrics, human-in-the-loop)
• Uses A/B testing to select models, retrieval methods, and prompting strategies
• Effective collaboration with non-technical stakeholders via iterative demos, feedback loops, and plain-language outputs

Reference Highlights

• Shipped production-ready AI/LLM solutions
• Took ownership of core architectural decisions and development
• Led significant aspects of design and implementation
• Works closely with users and iterates based on feedback
• Continuously improves systems via monitoring and maintenance
• Very effective cross-team collaborator
• Clear communicator who translates technical concepts well
• Explains complex systems in outcome/impact-focused terms for executives and clinical teams
• Uses best development practices for organized code collaboration