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.
• Please apply! Email us at founders@matx.com with your resume.

Silicon Engineer

We are looking for people who are excited about logic design and verification of efficient, powerful chips.

Responsibilities include:

• Design, implement, and test RTL for our hardware.
• Contribute to hardware architecture.
• For: arithmetic circuits, memory systems, network systems, processors, and more.

Preferred background:

• Excellent logic-design skills.
• Experience developing ASICs or FPGAs.
• Perhaps: strong software engineering skills.

Software Engineer

We are looking for people who are excited about writing fast low-level software. We primarily use the Rust programming language.

Responsibilities include:

• Write code that runs on our hardware.
• Write compilers targeting our hardware.
• Write simulators of our hardware.
• Advise on hardware architecture from a programmer's perspective.

Preferred background:

• Excellent software engineering skills.
• Perhaps: experience optimizing software, perhaps through parallelism, SIMD programming, C or assembly-level optimization, or GPU kernels.
• Perhaps: experience with compiler algorithms such as register allocation, instruction scheduling, instruction selection, loop optimizations.

ML Engineer

We are looking for people who are excited about systems-focused ML research.

Responsibilities include:

• Train and optimize LLMs for our hardware.
• Run quality evaluations.
• Build and set up distributed infrastructure for training and inference.
• Advise on the hardware architecture from an ML perspective.

Preferred background:

• Excellent software engineering skills.
• Experience training and tweaking neural networks, ideally LLMs.
• Perhaps: experience optimizing neural networks for hardware efficiency, for example regarding FLOPs, memory bandwidth, communication bandwidth, precision, parallel layout, batch sizes.