About the role:

ML developers today face significant friction in taking trained models into deployment. They work in a highly fragmented space, with incomplete and patchwork solutions that require significant performance tuning and non-generalizable/ model-specific enhancements. At Modular, we are building the next generation AI platform that will radically improve the way developers build and deploy AI models.

A core part of this offering is providing a platform that allows developers reuse deployment specific tuning and enhancements across model families and frameworks. As an AI Kernel Engineer you will own developing and tuning performance libraries for AI models. You will develop kernels and algorithms to increase performance of kernels, reduce the activation volumes, speedup data pre- and post-processing, and in general increase the end-to-end performance of the model.

LOCATION: Candidates based in the US or Canada are welcome to apply. You can work from our office in Los Altos, CA or remotely from home.

What you will do:

• Design and optimize high-performance ML numeric and data manipulation kernels/operators. 
• Utilize low-level C/C++/Assembly programming to achieve state of the art performance. Your work will also entail potentially introducing new novel compiler and tools support. 
• Work with compiler, framework, runtime and performance teams to deliver end-to-end performance that fully utilizes today’s complex server and mobile systems. 
• Collaborate with architects and hardware engineers to co-design future accelerators, including ISA for new hardware features and evolving ISA. 
• Collaborate with machine learning researchers to guide system development for future ML trends.

What you bring to the table:

• In-depth knowledge of C++ and low-level (micro)architectural performance is required.
• 4+ years of experience working on complex code and systems.
• Experience with performance modeling and performance data analysis.
• Understanding of Parallelization techniques for ML / HPC Acceleration.
• Deep interest in machine learning technologies and use cases. 
• Creativity and curiosity for solving complex problems, a team-oriented attitude that enables you to work well with others, and alignment with our culture.

Helpful, but not required: 

Some knowledge of compiler fundamentals is valuable, as is familiarity with kernel authoring paradigms (i.e., OpenMP, CUDA, Halide, Rise/Lift, or others) 

• Experience with performance profilers, performance data analysis tools, visualization tools, and debugging or experience working with embedded systems 
• Experience working with distributed/parallel programming models and an understanding of parallel hardware. 
• Experience developing firmware for accelerators and embedded programming. 
• Experience with HPC programming and accelerator languages such as CUDA, OpenCL, SYCL, etc.

The estimated base salary range for this role to be performed in the US, regardless of the state, is $166,500.00 - $242,000.00 USD. 
The estimated base salary range for this role to be performed in Canada, regardless of the province, is $157,500.00 - $228,500.00 CAD.
The salary for the successful applicant will depend on a variety of permissible, non-discriminatory job-related factors, which include but are not limited to education, training, work experience, business needs, or market demands. This range may be modified in the future. The total compensation for a candidate will also include annual target bonus, equity, and benefits, with equity making up a significant portion of your total compensation.

For candidates who fall outside of the listed requirements, we nevertheless encourage you to apply as we may have openings that are lower/higher level than the ones advertised.