Do you want to build products with a lower latency than a B200?

Do you want to push the boundaries of next-gen hardware acceleration for machine learning?

We are currently seeking Firmware Engineers to join a company building AI chips that are hard-coded for individual model architectures.

They are a very well-funded AI hardware startup ($125M Series A) and their first product has an order of magnitude more throughput and lower latency than a B200. With their ASICs, you can build products that would be impossible with GPUs, like real-time video generation models and extremely deep chain-of-thought reasoning.

As a Firmware Engineer, you will design, implement, and optimize firmware for ML accelerators, working closely with hardware and system architects. Your role will be critical in driving the performance, efficiency, and reliability of cutting-edge accelerator blocks, including systolic arrays and other novel architectures.

Requirements

• Experience in firmware development for RTOS embedded systems
• Experience working with high-speed interfaces (e.g. PCIe/DDR/HBM/Ethernet).
• Proficiency in C/C++ programming for embedded systems
• Experience with ARM/ARC/Xtensa/RISC-V embedded architecture
• Ideally, you will have experience with OCP/OAM/DTMF/Security standards too

This role is based in the Bay and is 5 days a week onsite.