d-Matrix is seeking machine learning researchers to invent, design, and implement efficient algorithms that will be used to optimize Large Language Model inference on DNN Accelerators.
Requirements
- Experience in Python and OOP code design
- Experience with transformer architecture is advantageous but not mandatory
Responsibilities
- invent, design, and implement efficient algorithms that will be used to optimize Large Language Model inference on DNN Accelerators we develop
- create and apply advanced algorithmic and numerical techniques to the most cutting-edge and high-impact research in the overlap of mathematics, ML, and modern LLM applications
Other
- Hybrid, working on-site at our Santa Clara, CA, headquarters 3 days per week.
- MSc or PhD in math, CS, statistics, physics, or a related STEM field
- humble expertise, kindness, dedication and a willingness to embrace challenges and learn together every day.
