MatX: faster chips for LLMs Come work with us! Whether we're working in hardware, software, or ML, we want our code to be efficient and to run fast. We like candidates who have shipped high quality solutions to real technical problems. We are interested in all experience levels, from new graduates to industry veterans. We work in person three days a week in our office in Mountain View, California. Here are some things we value: Consider new approaches. We are solving a different problem than previous products. Therefore our solutions will often be different. We readily abandon traditional or already-implemented approaches if there is an alternative that is better in our context. Understand deeply. We carefully reason through the consequences of big decisions. A few days of thinking can be worth more than weeks of simulation or months of experimentation. This is how we make big bets with high confidence. Invite and include. We are a high-trust team who supports each other and helps to develop the skills and understanding of each other. We take each other's contributions seriously and we make sure good ideas are heard, even and especially when they mean major shifts in direction.
Careers at MatX
MatX is on a mission to be the compute platform for AGI. We are developing vertically integrated full-stack solutions from silicon to systems including hardware and software to train and run the largest ML workloads for AGI. We primarily use the Rust programming language.
Responsibilities include:
- Design and optimize kernels that interface directly with our hardware
- Work in partnership with our ML Research and Hardware Engineering teams
- Provide expertise and guidance on hardware architecture from a programmer's perspective, ensuring seamless integration with the software stack
Requirements:
- Bachelor of Computer Science or equivalent degree
- Experience optimizing software for specialized hardware, employing techniques such as parallelism, SIMD programming, C, assembly-level optimization, or GPU/CUDA programming
- Language: at least one of assembly, C++, C, Zig, or Rust
Preferences:
- Experience implementing kernels for ML models such as Transformers
- Experience using and implementing distributed parallelism techniques such as AllReduce, AllToAll, data parallelism, tensor parallelism.
- Familiarity with how compilers work
Compensation
- The US base salary for this full-time position is $120,000 - $400,000 + equity
Benefits
- Commuter stipend available for employees within 60 minutes of the office
- 401(k) with contribution matching
- Health, vision, and dental insurance
- Life and AD&D insurance
As part of our dedication to the diversity of our team and our focus on creating an inviting and inclusive work experience, MatX is committed to a policy of Equal Employment Opportunity and will not discriminate against an applicant or employee on the basis of race, color, religion, creed, national origin or ancestry, sex, gender, gender identity, gender expression, sexual orientation, age, physical or mental disability, medical condition, marital/domestic partner status, military and veteran status, genetic information or any other legally recognized protected basis under federal, state or local laws, regulations or ordinances.
All candidates must be authorized to work in the United States and work from our offices in Mountain View Tuesdays-Thursdays.
This position requires access to information that is subject to U.S. export controls. This offer of employment is contingent upon the applicants capacity to perform job functions in compliance with U.S. export control laws without obtaining a license from U.S. export control authorities.
MatX does not accept unsolicited resumes from individual recruiters or third-party recruiting agencies in response to job postings. No fee will be paid to third parties who submit unsolicited candidates directly to our hiring managers or People team and any resumes submitted are deemed to be the property of MatX.