PromotedHiringCafe
ML Engineer - Inference & Model Deployment
Cupertino, CA, US
$250k-$310k/yr On-SiteFull Time
Turn powerful AI and ML models into fast, reliable production systems. Own inference latency, throughput, model-serving architecture, multi-GPU systems, and production deployment for millions of users.
Python, PyTorch, vLLM, SGLang, TensorRT, LLMs
4w
Save
Mark Applied
Hide
Manager, Engineering - App Engine (CUDA)
Ann Arbor or Blacksburg or Fort Worth or United States
$161k-$193k/yr HybridFull Time
3+ MgmtBachelor's or Master's in a technical field, 3+ years people management, deep expertise in CUDA/GPU parallel computing, C++ and Linux, experience with PyTorch/TensorRT/ONNX and model deployment, safety-critical systems knowledge.
CUDA, PyTorch, TensorRT, ONNX, C++, Linux