Principal Engineer, Model Performance

Remote (Restricted)senior
United States
Confirmed open1 hour ago
First seentoday
Remoet re-checks every listing roughly once a day.
Apply on RunwareYou will apply on Runware's own site.Star Runware to hear about new roles →

Senior principal engineer role for AI inference performance, remote-restricted to the United States.

Summary, tech stack, seniority and salary here are extracted or inferred by Remoet, not the employer's own words.

Tech stack

CUDAPythonC++PyTorchtorch.compileTritonTensorRT-LLMvLLMSGLangFlashAttentionCUTLASSDynamoNsight SystemsNsight ComputeNCCL

Benefits

Stock optionsPaid time offVacationSick daysPublic holidaysPaid maternity leavePaid paternity leavePaid caregiver leaveTwice-yearly company retreats
Confirmed open1 hour ago
First seentoday
Remoet re-checks every listing roughly once a day.
Apply on RunwareYou will apply on Runware's own site.Star Runware to hear about new roles →