Inference & model-serving jobs

Serving roles — GPU, Triton, TensorRT, quantization, latency and throughput.

510 open roles

Open roles
510
Median salary
$245k

median of 239 priced roles, USD

Remote
11%

plus 16% hybrid

Top skill
GPU

in 82% of roles

Hiring most:Nebius23Adobe19Cerebras16Inferact16Capital One13Together AI13

Common stack:GPU420Python370PyTorch235Kubernetes205Orchestration186Go148C++133AWS129Quantization125vLLM116

← All jobsRSS feed