JOBS / Cerebras

ML Research Scientist - Inference ML

United States and Canada

Role

The role involves inventing and evaluating advanced algorithms for efficient inference on Cerebras hardware, focusing on speculative decoding, pruning, and sparse attention. Candidates must have a PhD or master's degree with significant research experience and strong Python skills.

Location: United States and Canada
Employment: unspecified
Work pattern: hybrid
Seniority: senior

PythonPyTorchSpeculative DecodingModel CompressionSparse Attention

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Ashby feed. Source update: 2026-10-02T23:45:55.090+00:00. Check the employer’s page for the complete description, current availability and application terms.

Cerebras RESEARCH PROFILE ↗