I am a M.S. Computer Science student @Northeastern University. My expected graduation date is between Dec, 2025 and May, 2026.
I’m passionate about machine learning and large language models (LLMs), from building them from scratch to making them run fast in the real world. I’ve worked on training and aligning LLMs, scaling them efficiently across GPUs, and deploying them in applications like game recommendation and flashcard generation. Recently, I’ve also focused on making LLMs faster, cheaper, and more efficient—whether in the cloud with vLLM or on edge devices with quantization.
Here's a handful selection of my recent experience:
-
Designed a housing inventory prediction model during a machine learning engineer intern @Berkshire Hathaway HomeServices.
-
Built @a framework to asynchronously schedule tasks during deep learning tensor computation with 4x performance improvement in parallel request query.
I am eager to contribute to open-source projects and volunteer with organizations that promote the common good. Feel free to reach out if you’d like to collaborate or connect.