Want to build the future compute platform for AGI?t

Want to build hardware and software to train and run the largest ML workloads for AGI?

We are currently looking for ML Performance Engineers to join a company focusing on becoming THE compute platform for AGI.

The company has over $80 million in Series A funding and are enhancing AI by building powerful hardware, specifically tailored for Large Language Models (LLMs).

They have a top-tier founding team spinning out of Google’s PaLM and with their hardware, individual researchers can train 7B-class models from scratch every day, and 70B-class models multiple times per month.

As an ML Performance Engineer, you will write production-grade libraries for efficient distributed training and serving, as well as build performance models and tooling to validate and guide scheduling decisions.

Requirements

• Bachelor of Computer Science or equivalent degree
• Experience in Python as well as ML frameworks such as JAX, PyTorch, or Tensorflow
• Deep knowledge of the Transformer architecture and experience with distributed computing, high performance networking, or large-scale ML systems

This role is hybrid in the Bay Area