Full Time: Jan 2026 - Present
Intern: May 2025 - Aug 2025
Lead backend and LLM engineer on a generative AI system that drafts clinical referral documents from patient records and notes, replacing a 30+ minute manual process; built the FastAPI/Python orchestration layer, retrieval pipeline, and multi-model (Claude, Gemini) synthesis service on Vertex AI.
Designed note-processing and retrieval components: chunking, embeddings, negation and POS detection, cross-encoder ranking.
Built an LLM evaluation service for scoring outputs with reproducible, auditable runs, and stood up production LLM observability (OpenTelemetry / MLflow) for cost, latency, and token attribution.
Built an MCP hub to authenticate and connect Agents, with OAuth2 authentication, A2A, and live server / tool discovery.
Machine Learning Graduate Intern (May 2025 – Aug 2025)
Designed and built a chatbot development platform end to end, spanning frontend (HTML/CSS/JS), backend (Python/REST), and retrieval augmented generation with knowledge graph based memory that outperformed off the shelf solutions.
Researched and implemented advanced ML Models, largely combinations of
CNN, LSTM, Transformer, GNN, and XGBoost
Collected and processed Satellite data to be used in advanced ML algorithms, predicting floods, deforestation, atmospheric conditions, and more
Created front and back end of an application to allow the user to select area of interest, and model to be used, with automatic download and processing of large amounts of satellite data