About the role

Software Engineering Intern at d-Matrix developing high performance kernels for accelerating Machine Learning models. Collaborating with the Kernels team to implement, test, and tune kernels.

Responsibilities

Develop high performance kernels essential for accelerating Machine Learning models
Develop reference implementations for accuracy verification
Define unit tests for implemented operators
Performance tuning and scalability analysis across varied problem sizes
Collect performance metrics and identify bottlenecks to improve core functionality
Package and ship the final implementations

Ability to implement high performance kernels in low-level languages; Assembly/ISA coding experience is advantageous
Proficiency in Python and/or C++
Solid background in Machine Learning model architecture (e.g., LLMs, CNNs)
Experience with ML frameworks such as PyTorch and ML packages like Numpy
General understanding of computer architecture (CPU, GPU, custom ASICs, etc.)
Currently enrolled in a graduate program (Master's or Ph.D) in a relevant discipline
Previous internship or project experience related to high performance computing or ML kernel development preferred
Familiarity with additional ML frameworks (TensorFlow, etc.) preferred
Interest in hardware-software co-design preferred

Medical/Dental/Vision/401k
Diverse package of benefits centered around the wellbeing of our employees and their loved ones
Incentive opportunities based on individual and company performance