• - Building full-stack features across a Python/Django backend and React/TypeScript frontend, with a focus on reliability and performance at scale. Designed and shipped RAG pipelines and multi-agent systems that bring LLM capabilities into production workflows. Own end-to-end delivery across backend APIs, database modeling (PostgreSQL), and cloud infrastructure (AWS) — from architecture to deployment.

• - Built systems to capture data for clients/customers during inspections and on-site services that lead to better customer satisfaction and increases unit reliability for owners and manufacturers.

• - Contributed to full-stack feature development on an engineering team with focus on RAG pipeline for insurance and clinical bots. Worked across the stack building backend services and UI components, collaborating async across timezones. Focused on delivering clean, testable code with a short feedback loop between design and production.

• - Selected for an intensive AI engineering fellowship focused on shipping real products fast. Built and deployed multiple AI-powered applications over the course of the program, working with LLMs, vector databases, and modern full-stack tooling. Emphasis on rapid prototyping, user feedback loops, and taking ideas from zero to deployed.

• - Contributed to applied ML and NLP research at the intersection of human psychology and language models. Built infrastructure to support research experiments, processed and analyzed large datasets, and implemented models to study how AI systems behave and interact with human cognition. Bridged the gap between research insights and reproducible, engineered systems.

• - Graded assignments, and ran review sessions — essentially debugging other people's mental models before debugging code became the job.