Hi, I'm Julian. I'm a CS student at Stanford (BS '27, MS '28). For my master's degree and my work as a research assistant at the Scaling Intelligence Lab, I'm fortunate to be advised by Prof. Azalia Mirhoseini.

My work primarily centers on inference and ML systems. Most recently, I completed my second internship at NVIDIA optimizing inference with multithreaded PyTorch and CUDA Graphs, and my second internship at Duolingo making content generation safer and more scalable with the Content Infrastructure team.