About Etched

Etched is building AI chips that are hard-coded for individual model architectures. Our first product (Sohu) only supports transformers, but has an order of magnitude more throughput and lower latency than a B200. With Etched ASICs, you can build products that would be impossible with GPUs, like real-time video generation models and extremely deep chain-of-thought reasoning.

Firmware Engineer, Machine Learning Validation

We are looking for a Firmware Engineer with experience validating machine learning accelerator silicon with high-speed interfaces. The ideal candidate will be able to design validation plans, write validation tests, and debug both software and hardware issues on custom machine learning accelerator silicon in the lab.

Representative projects:

• Design validation plan for silicon bring-up.
• Develop tests and debug both software and hardware bugs in the lab.
• Optimize performance of silicon with hardware software co-design.
• Collaborate closely with both hardware, firmware, and software engineers to comprehend architecture and specifications.
• Validate tests in both simulation and emulation environments before silicon shows up.

You may be a good fit if you have:

• 5+ years of experience in silicon validation and debugging.
• 2+ years of experience with machine learning algorithms, such as transformer or CNN.
• Ability to learn quickly and have an open-minded mindset.
• Experience working with simulation and emulation environments.
• Proficiency in C/C++ programming for embedded systems.
• Experience with hardware validation and debugging tools (e.g. OpenOCD/Segger/Lauterbach).
• Experience with ARM/ARC/Xtensa/RISC-V architecture.
• Experience with electronics lab equipment (e.g. oscilloscopes and protocol analyzers).
• Experience with production silicon and system lifecycle.

Strong candidates may also have experience with:

• Experience with SystemVerilog language and debugging with waveforms.
• Experience with Python language in scripting and automation.
• Experience with Bazel/Blaze/Buck build system.

How we’re different:

Etched believes in the Bitter Lesson. We think most of the progress in the AI field has come from using more FLOPs to train and run models, and the best way to get more FLOPs is to build model-specific hardware. Larger and larger training runs encourage companies to consolidate around fewer model architectures, which creates a market for single-model ASICs.

We are a fully in-person team in Cupertino, and greatly value engineering skills. We do not have boundaries between engineering and research, and we expect all of our technical staff to contribute to both as needed.

Benefits:

• Full medical, dental, and vision packages, with 100% of premium covered, 90% for dependents
• Housing subsidy of $2,000/month for those living within walking distance of the office
• Daily lunch and dinner in our office
• Relocation support for those moving to Cupertino