Global AI MapJOBS / Liquid AI
Member of Technical Staff - GPU Performance Engineer
San Francisco; Remote; Boston
Role
The role involves designing and shipping custom CUDA kernels to optimize GPU performance for AI training and inference pipelines. Candidates must have strong C/C++ skills, proficiency with low-level profiling tools like Nsight, and a deep understanding of GPU architecture and memory hierarchies.
Location: San Francisco; Remote; Boston
Employment: full time
Work pattern: hybrid
Seniority: mid
APPLY ON THE EMPLOYER’S SITE ↗
Source and currency
This vacancy came from the organization’s official Ashby feed. Source update: 2025-07-29T20:46:39.065+00:00. Check the employer’s page for the complete description, current availability and application terms.