Join a world-class team of builders combining deep hardware and software expertise to invent a revolutionary consumer product! We're looking for engineers to help turbocharge our serving layer, optimizing the performance of cutting-edge LLM, speech, and vision models, experiment with new compilers to support running models on a variety of hardware compute platforms and write custom kernels. If you're excited about shaping the future of real-time AI systems, we’d love to talk.

Note: This role requires candidates already within the mainland United States and 4 years of professional industry experience as a ML Performance or Infrastructure Engineer.

Locations: Bellevue WA, San Francisco CA, New York City, NY.

Required Qualifications: