Hi! I'm Ryan.
Incoming SWE // Neuralink ðŸ§
SWE // General Dynamics Mission Systems 📡
Biomedical Engineering // Waterloo 
Currently, I'm building an inference cluster for my home lab setup.
Lately, I've been thinking about:
- splitting spec decode across nodes
- how much precision models actually need
- bottlenecks in inference time
Reach out anytime!