Staff Software Engineer - GenAI inference

Role

This role involves leading the architecture and optimization of Databricks' GenAI inference engine for the Foundation Model API. Candidates must have strong software engineering experience in performance-critical systems and deep knowledge of ML inference internals, CUDA, and distributed systems.

Location: San Francisco, California
Employment: full time
Work pattern: unspecified
Seniority: senior

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Greenhouse feed. Source update: 2026-09-21T13:22:12-04:00. Check the employer’s page for the complete description, current availability and application terms.

• databricks.com/company/careers/open-positions/job ↗

Databricks RESEARCH PROFILE ↗