Background.
Studied engineering mechanics at UW–Madison, then moved to Pittsburgh for a master's in AI at CMU. Now in Seattle, working at Armada.
Most of my work right now is on time-series forecasting and edge inference, getting models to run on hardware that wasn't designed for it. I also spend time on multimodal agents: systems that can look at something, figure out what to do, and follow through without falling apart when the inputs change.
Skiing, running, hiking, paddleboarding. Good city for it.
Selected work.
SCOPE
When you chain a language model and a vision model together, how do you know which one failed? SCOPE is an evaluation harness for modular multimodal pipelines, built around PTZ camera control as the test domain. Published at HRI '26.
- Python
- Blender
- Qwen3
- Moondream
- vLLM
- LLM-as-Judge
Fine-tuning LLaVA for Web Agents
Group project at CMU. We took LLaVA, fine-tuned it on VisualWebBench, and pushed the open-model score up.
- LLaVA
- LoRA
- PyTorch
- VisualWebBench
Waste Classification on a Raspberry Pi 5
Vision classifier squeezed onto a Pi 5 to run offline. The constraints ended up being more interesting than the model.
- ONNX
- Raspberry Pi 5
- OpenCV
- INT8 quantization
Refueling Satellite
Senior design capstone at UW. Designed and analyzed a concept for refueling satellites on orbit.
- SolidWorks
- ANSYS
- MATLAB
Directional Buckling for In-Pipe Locomotion
Soft robotics work at CMU. Designed a compliant leg that buckles in a known direction so a small robot can walk through narrow pipes.
- ANSYS
- Silicone elastomer
- 3D printing
Beach Cleaning Device
Senior design capstone at UW. A sand-sifter for picking microplastics out of beaches.
- CAD
- Mechanical prototyping
- Field testing
↳ Click any row for the longer version. Source on GitHub.
What I follow.
Lately it's been time-series forecasting and edge inference — quantized models running on hardware with no cloud, no GPU, limited everything. Also multimodal agents: systems that can look at something, figure out what to do, and follow through without falling apart when the inputs change.
Always been curious about how things work — that's what led me to engineering. Solving problems, connecting dots. The move from mechanical systems to AI was natural; the questions are the same, the tools just changed.
Running, skiing, hiking, paddleboarding.