SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 175,000 - 400,000 / annual
MatX is building a vertically integrated full-stack compute platform for AGI, spanning hardware and software to train and run the largest ML workloads. The company primarily uses Rust and is seeking a Software Engineer to design and optimize kernels that interface directly with custom hardware.
In this role, you will design and optimize kernels that interface directly with MatX's hardware, working in close partnership with ML Research and Hardware Engineering teams. You'll provide expertise and guidance on hardware architecture from a programmer's perspective, ensuring seamless integration between the software stack and hardware capabilities.
You should have a Bachelor's degree in Computer Science or equivalent, with hands-on experience optimizing software for specialized hardware using techniques such as parallelism, SIMD programming, C, assembly-level optimization, or GPU/CUDA programming. Proficiency in at least one of assembly, C++, C, Zig, or Rust is required.
Bonus qualifications include experience implementing kernels for ML models like Transformers, familiarity with distributed parallelism techniques (AllReduce, AllToAll, data parallelism, tensor parallelism), and knowledge of compiler internals.
This is a hybrid role requiring 3 days per week in the Mountain View office (Tuesday–Thursday), with flexibility to work remotely on Monday and Friday. The company offers competitive compensation with equity, comprehensive health and wellness benefits, 4 weeks paid time off, professional development support, and various perks including commute assistance and home-tech setup for remote work.
