Electrical Engineer, Hardware Systems

5-10 years of experience in complex server/switch system design and development

Extensive experience on 100G Ethernet, PCIe Gen5, I2C, SPI, UART interfaces

Familiar with modern AI/datacenter system architecture

Proven track record of designing systems alongside silicon

Deep understanding of datacenter needs, especially with respect to high power (>10 kW) AI servers

Passionate about modern AIs like ChatGPT, and willing to learn about them on the job

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

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 do not have boundaries between engineering and research, and we expect all of our technical staff to contribute to both as needed.

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.