INFERENCE CAREERS · FREE TO BROWSE
Inference engineer jobs.
Work on the path from model weights to served tokens. Explore recent openings in LLM serving, GPU kernels and inference performance, with links straight to the hiring team's listing.
Explore recent openings
Full descriptions on employer sites16 roles
Sr. Software Engineer, Training/Inference (C++) (opens in a new tab)
Palo Alto, CA
Inference engines & serving
xAI (SpaceXSI) interview prepView rolePostedCheckedSr. Software Engineer, Kernels/CUDA (C++) (opens in a new tab)
Palo Alto, CA
GPU kernels & compilers
xAI (SpaceXSI) interview prepView rolePostedCheckedSenior Software Engineer, ML API – AI Inference (opens in a new tab)
Toronto, CAN · Sunnyvale, CA / Hybrid / Full time
Inference engines & serving
Cerebras interview prepView rolePostedChecked(Senior/Junior AI Inference Reliability Engineer, Compute Infra (opens in a new tab)
San Francisco
Inference engines & serving
Together AI interview prepView rolePostedCheckedCompiler Engineer - New Grad (opens in a new tab)
Austin, Texas, United States; San Jose, California, United States
GPU kernels & compilers
SambaNova Systems interview prepView rolePostedCheckedStaff Software Engineer, GPU Inference (opens in a new tab)
Toronto, CAN · Sunnyvale, CA / Hybrid / Full time
Inference engines & serving
Cerebras interview prepView rolePostedChecked(Staff / Senior Staff) AI Inference Reliability Engineer, Compute Infra (opens in a new tab)
San Francisco
Inference engines & serving
Together AI interview prepView rolePostedCheckedAI Performance Engineer - New Grad (opens in a new tab)
Austin, Texas, United States; San Jose, California, United States
Inference performance
SambaNova Systems interview prepView rolePostedCheckedSoftware Engineer, TPU Compilers (opens in a new tab)
San Francisco / Hybrid / Full time
GPU kernels & compilers
OpenAI interview prepView rolePostedCheckedResearch Engineer, GPU Performance (opens in a new tab)
Paris / Full time
Inference performance
Mistral AI interview prepView rolePostedCheckedEngineering Manager, Inference Router (opens in a new tab)
Sunnyvale, CA · Toronto, CAN / Hybrid / Full time
Inference engines & serving
Cerebras interview prepView rolePostedCheckedEngineering Manager, Inference Performance (opens in a new tab)
San Francisco · New York / Hybrid / Full time
Inference performance
Baseten interview prepView rolePostedCheckedResearch Engineer, Inference Foundation (opens in a new tab)
Munich · Warsaw · London / Hybrid / Full time
Inference engines & serving
Mistral AI interview prepView rolePostedCheckedSoftware Engineer - Inference Platform (opens in a new tab)
San Francisco · Toronto · New York · Montreal · Seattle / Hybrid / Full time
Inference engines & serving
Baseten interview prepView rolePostedCheckedSoftware Engineer - Inference Performance (opens in a new tab)
San Francisco · Toronto · New York · Montreal · Seattle / Hybrid / Full time
Inference performance
Baseten interview prepView rolePostedCheckedMember of Technical Staff - Inference Runtime (opens in a new tab)
San Francisco / On-site / Full time
Inference engines & serving
Modal interview prepView rolePostedChecked
Remote listings can still restrict eligible countries. Check the employer's page for location, visa and work arrangements.
What makes this list
Serving work, from runtime to kernel
We review roles for work on inference engines, model execution, GPU kernels or serving performance. Company links lead to interview preparation for the systems that team builds.
A 45-day publication window
Posted dates come from the employer's feed. A republished role can appear again. Checking a listing does not reset its posted date. Undated, removed and older roles are omitted; a check older than 21 days is flagged.
The employer handles applications
Follow the role link for requirements and current availability. This independent board stores listing details only. Applications and recruiting decisions stay with each employer.