On an AI Governance, Evaluation & Monitoring Platform, I developed AI/LLM evaluators for measures including semantic similarity, precision, recall, groundedness, and fluency. I also built React/Next.js interfaces and extended FastAPI endpoints for evaluation and result inspection.
For a Data Analytics Chatbot, I worked on backend development and ML tools, using LLMs to analyze and orchestrate chatbot behavior. I also created analytical and mathematical tools to extend its capabilities.
On an AI SaaS platform for natural language understanding, I implemented backend features, API integrations, and infrastructure deployments. I also contributed to monitoring, testing, and the migration from Jenkins and Terraform to GitHub Actions and AWS CDK.

