About Me
I'm currently a Member of the Technical Staff at AMD accelerating the performance of open source LLMs. Previously, I was a Senior Research Engineer at Qognitive where I designed and implemented efficient numerical methods for machine learning and quantum computing algorithms. Before that, I was a Member of the Technical Staff at Lucata where I worked on porting GraphBLAS to Lucata's custom hardware. My work focused on implementing highly parallel linear algebra methods in C/C++. Before that, I was a Flatiron Research Fellow in the Center for Computational Quantum Physics at the Flatiron Institute, developing more efficient and robust algorithms for quantum chemistry. For a detailed description of my experience and publications, please see my resume.
Software
I contribute to a number of open source software projects, here are a few:
AITER
A library of optimized GPU kernels and primitives for AI workloads on AMD GPUs.
vLLM
A fast and easy-to-use library for LLM inference and serving.
Deep Graph Library
A port of the Deep Graph Library (DGL) for compatibility with AMD GPUs.
Fast Pauli
A fast and memory efficient library for evaluating and simulating Pauli strings for quantum computing and machine learning.
PySCF
An accessible Python package for quantum chemistry.
Dice
Implementation of the heat-bath configuration interaction (HCI) algorithm for strongly correlated quantum chemistry calculations.
FRI-CC
The fast randomized iteration algorithm applied to coupled cluster methods.
Blog
Thoughts and tutorials on scientific computing, quantum chemistry, and software development.
Talks
- CMake Intro Lucata Inc. Internal Meeting 2023
- PySCF Overview Talk, CCQ Retreat 2021
- SHCI: A Semi-Pedagogical Introduction, Berkelbach Group Meeting 2020