
Solo
An autonomous unmanned ground vehicle built with Project Manas for the Intelligent Ground Vehicle Competition (IGVC) at Oakland University. Helped win IGVC 2019 and several other awards.
Software engineer building Agents, Evals and Harnesses @ Microsoft · Grand Award winner @ ISEF 2017
I build agentic AI systems — currently shipping multi-agent orchestration and eval frameworks for Microsoft 365. Before that, end-to-end ML at an early-stage startup, across time-series forecasting, LiDAR segmentation, and computer vision. My core expertise spans LLM orchestration, RAG, prompting & evaluation, and distributed systems — data pipelines, event processing, observability.
Core contributor to Team Copilot's multi-agent orchestration engine — task decomposition, agent tooling, enterprise grounding, and LLM-judge eval frameworks across Microsoft 365.
Owned three production ML systems end-to-end at an early-stage startup: solar performance-loss prediction, bathymetric LiDAR segmentation, and Siamese-network video auto-labeling.
Client-side caching cut page load time by 73%; built the Planner → Project import flow.
Organised expert talks, workshops, and competitions for the student chapter.

An autonomous unmanned ground vehicle built with Project Manas for the Intelligent Ground Vehicle Competition (IGVC) at Oakland University. Helped win IGVC 2019 and several other awards.

A smartphone-based vein-imaging system that uses visible-spectrum image processing to visualize subcutaneous veins without IR hardware, aimed at making IV access easier for nurses. Won Second Place Grand Award in Biomedical Engineering at Intel ISEF 2017 and the Grand Award at IRIS 2016.

An AR/VR microscope on the Google Cardboard platform, operated hands-free by voice while exploring biological samples, doubling as a dental loupe and a live-streaming tool for remote guidance. Selected top 90 globally, Google Science Fair 2015.
A real-time voice-agent platform: a streaming ASR → LLM → TTS pipeline over SIP/WebSocket with VAD, turn-taking, and barge-in, built on the OpenAI APIs. Sub-1,000ms p95 end-to-end latency.

Named by MIT Lincoln Laboratory's Ceres Connection program, following the Second Place Grand Award in Biomedical Engineering at Intel ISEF 2017.

Filed at Microsoft, for risk assessment and mitigation recommendations in projects, and for better context extraction for task execution.
Microsoft internal hackathon wins, with multiple ideas adopted into the product roadmap.