About the job
What MatX Is Building
At MatX, we are committed to creating the compute platform for Artificial General Intelligence (AGI). Our team is developing comprehensive full-stack solutions that encompass both hardware and software, designed to efficiently train and execute the largest machine learning workloads for AGI. Our primary programming language is Rust.
What You'll Do Here
- Design and optimize kernels that interact directly with our hardware architecture.
- Collaborate closely with our Machine Learning Research and Hardware Engineering teams.
- Provide programming insights and guidance on hardware architecture to ensure seamless software integration.
Who You Are
- Bachelor's degree in Computer Science or a related field.
- Experience in optimizing software for specialized hardware using techniques like parallelism, SIMD programming, C, assembly optimization, or GPU/CUDA programming.
- Proficient in at least one of the following languages: assembly, C++, C, Zig, or Rust.
- This is a hybrid position requiring you to work in our Mountain View, CA office 3 days a week (Tuesday through Thursday).
Bonus Points If You Have
- Experience with kernel implementations for machine learning models, including Transformers.
- Familiarity with distributed parallelism techniques like AllReduce, AllToAll, data parallelism, and tensor parallelism.
- Understanding of compiler operations.
Compensation
Compensation for this full-time role is based on several factors including experience, skills, and location. Career length is considered as a guideline for salary.
- 0-5 years of experience - $120,000 - $200,000 + equity
- 5-10 years of experience - $120,000 - $300,000 + equity
- 10+ years of experience - $120,000 - $400,000 + equity
What We Offer
- A Stake in Our Success: A competitive cash/equity mix tailored to your needs, with the option for early exercise.
- Health & Wellness: Comprehensive health, dental, vision, and life insurance, along with pre-tax Health Savings Accounts featuring generous contributions.
- Time To Recharge: 4 weeks of paid time off (accrued), 12 company holidays, and additional time off for personal needs.

