4 inference optimization engineer jobs at 2 companies in San Diego, CA
1w
Save
Mark Applied
Hide
Machine Learning Performance Engineer - Offboard Training & Inference
Sunnyvale or Washington, D.C. or San Diego or Fort Walton Beach or Ann Arbor or London or Stuttgart or Munich or Stockholm or Bangalore or Seoul or Tokyo
$215k-$285k/yr OnsiteFull Time
ML performance engineering experience with distributed training, batch inference, GPU or accelerator optimization, Python, and C++ or another systems language; strong debugging and analytical skills required.
FSDP, DeepSpeed, Megatron, NCCL, NVIDIA Triton Inference Server, TensorRT, ONNX Runtime, Ray, Python, C++, CUDA, Triton, CUTLASS, Nsight Systems, Nsight Compute, PyTorch Profiler, perf, Kubernetes, Slurm, ROS, OpenCV
1mo
Save
Mark Applied
Hide
Senior Engineer - Machine Learning
San Diego, California, United States
$141k-$211k/yr OnsiteFull Time
1+ YOEExperience designing and deploying production ML systems, inference optimization, model integration, and data pipeline engineering; strong programming skills (Python and a systems language); degree in CS/Engineering/Information Systems.
Python, C++, Rust, Go, PyTorch, TensorFlow, vLLM, ONNX, Kubernetes, Docker, CI/CD, OpenSearch, Qdrant
2mo
Save
Mark Applied
Hide
Datacenter AI Systems and Solutions Engineer, Sr Staff
San Diego, California, United States
$163k-$244k/yr OnsiteFull Time
4+ YOEBachelor's+ with 6+ yrs (or Master’s+5, PhD+4) systems engineering experience; strong Python, REST/APIs, GitOps, Docker, Kubernetes; experience designing, deploying, and optimizing large-scale AI/ML systems and inference solutions.
Python, APIs, REST, GitOps, Docker, Kubernetes, Slurm, PBS
2mo
Save
Mark Applied
Hide
Staff/Sr. Staff Software Engineer, AI Software Tools (Onsite)
San Diego or Raleigh
$158k-$238k/yr OnsiteFull Time
6+ YOEBachelor’s/MS/PhD in CS or related with 6+ years (Staff) / 8+ years (Sr. Staff) software experience; 3+ years AI/ML inference or model optimization; proficiency in Python, C/C++; experience with PyTorch and ONNX.
Python, C/C++, PyTorch, ONNX, ONNX Runtime, ExecuTorch, TFLite, LiteRT, Qualcomm AI Stack SDK, QAIRT, QNN, Genie, Hugging Face, PEFT, CMake, git, QNX, Android, Snapdragon SoCs, NPU