Tej Sidda

About

Built both a fantasy sports analytics product and a privacy-sensitive AI assistant for therapists, showing range across consumer and healthcare use cases. Particularly notable for designing self-hosted, HIPAA-conscious LLM systems with RAG, structured outputs, observability, and human-in-the-loop guardrails for clinical workflows.

Key Strengths

• End-to-end full-stack product ownership
• Creative API reverse engineering for product development
• Performance optimization via caching and predictive preloading
• Strong TypeScript data contract design
• HIPAA-conscious AI system design
• Self-hosted LLM deployment for privacy-sensitive use cases
• RAG architecture for grounded clinical summaries
• Structured LLM output enforcement with Pydantic
• LLM reliability improvement through self-correction loops
• Production AI observability with LangSmith and Langfuse
• Evaluation-driven iteration using tracing and CI/CD gates
• Thoughtful human-in-the-loop design for clinical risk mitigation
• Ability to ship MVPs quickly in ambiguous early-stage environments
• 85% recovery rate on failed structured-output generations

Experience

Education

Skills

Languages