UC Berkeley
the best soda is cherry coke zero
Currently interested in cloud infrastructure, distributed systems, and inference engineering, particularly cluster orchestration and Kubernetes. Working in the HyperPod team at SageMaker I got to work on the development of an inference operator, conducting intelligent routing for inference traffic, where I ended up interacting with vLLM internals, introducing me to the inference side which I'm particularly interested in learning more about. Also love the startup space, particularly coming up with fun new ideas and the people in it. Currently learning ML, Systems, how to make house music, and DJ.
Sponsorship Director at Cal Hacks. Reach out at collin@hackberkeley.com.
I am interested in building at the infrastructure level, the behind the scenes that power others.
Wrap your LLM client with one line of Python and every call, token, cost, and source location shows up in your dashboard in real time. Built to make agentic AI costs visible per agent, per function, and per line of code before they surprise you.
Multi-agent system that reconciles LiDAR canopy models, point cloud data, and field surveys to classify tree height bias and uncertainty.
Minimal transformer inference engine from scratch in C++. Core focus is the KV cache manager, the scarce resource that determines throughput in distributed LLM serving.
Built in USC's SEP. Automates medical referral intake, OCR to structured extraction to EMR auto-fill. Taught me more about customer discovery and what people actually pay for than any technical work.
One of my first full projects, built with friends at Cal Hacks. Analyzes news article bias with GPT-4 scoring and Hume AI sentiment, then rewrites the piece from three perspectives.
I really like to read about things that show new ways to think about things.
4.6, amazing worldbuilding, and ideas of politics, religion, control, etc
3.9, great, but definitely not as good as the first
4.0, Again, but good
4.9, probably my favorite book
3.2, fun story, nothing too crazy
3.5, remember it being decent
4.1/5 Loved this book, there were some moments where the science dragged on a bit, but overall amazing
1st book 4.3/5, 2nd 3.9, 3rd 3.3, great series though
My childhood