AI Runtime System Software Engineer - Linux Kernel

What MatX Is Building

MatX's mission is to make the world’s best AI models run as efficiently as allowed by physics, bringing the world years ahead in AI quality and availability. MatX is seeking silicon verification engineers to join our team as we create best-in-class silicon for high-performance and sustainable GenAI. Successful candidates for these roles will be responsible for delivering performant and functionally accurate silicon for MatX products across compute, memory management. High-speed connectivity and other key technologies.

Your Place Here

As an AI Runtime System Software Engineer reporting to our Systems Software Lead, you'll contribute to the System Software Team. You'll join a talented group of engineers helping us to create best-in-class silicon for high-performance and sustainable GenAI. As part of a small team, you'll help see your ideas come to life and see the impacts of your work.

What You'll Do Here

• Work closely with the architecture teams, silicon design teams and other software/firmware teams to architect, design, and implement scalable and high-performance system software components, including device drivers in Linux, low-level libraries and daemons
• Deliver unit-tests for all software components being developed, including kernel level softwares
• Collaborate with ML and compiler teams to understand how to optimize the system software stack and optimize ML training and inference workloads
• CPU/memory subsystem optimization for the host system stack
• Optimize movement of ML data to and from the accelerator, job scheduling, synchronization etc
• Write debug and performance monitoring utilities
• Performance profiling, look for opportunities to reduce operating system overheads
• Influence the design of next generations of accelerators, and the host system software stack
• Design system software components to improve system observability, improve resiliency
• Design and implement cluster management solutions and failover algorithms to minimize downtime
• Bring up and help debug issues during new chip bring-up in close collaboration with hardware engineers
• Productize system software stack across various CPU ISAs and operating system versions

Who You Are

• BS or higher in Electrical Engineering or Computer Science, with 8+ years of experience in the following areas
• Strong hands-on development experience in Linux, both in low-level userspace libraries as well as device drivers in the Linux kernel
• Ability to read hardware data sheets, register definitions etc. to program hardware devices
• Experience in user-facing software bring-up on new custom silicon
• Strong C programming skills
• In-depth knowledge of computer hardware and system architecture
• Good understanding of low-level operating systems interfaces - threads, process management, memory management etc
• Experience debugging issues related to complex hardware-software interaction
• This is a hybrid role that will require you to work from our Mountain View, CA office 3 days a week on Tuesday through Thursday

Bonus Points If You Have

• Experience in hardware bring-up, simulation and emulation environments
• Good understanding of system level architecture, interrupts, memory mapped IO, direct memory access, computer systems interconnect, memory hierarchy etc
• Performance tuning and optimization in kernel drivers and modules, low-level libraries

Compensation

The US base salary for this full-time position is determined based on a variety of factors including role, experience, location, job related skills, and relevant education and training. Career length is only a guideline for compensation.

• 0-5 years of experience - $120,000 - $200,000 + equity
• 5-10 years of experience - $120,000 -$300,000 + equity
• 10+ years experience - $120,000 - $400,000 + equity

What We Offer

• A Stake in our success A cash/equity mix that fits your needs and option to do early exercise