3 gpu inference performance engineer jobs at 3 companies in North Carolina
1mo
Save
Mark Applied
Hide
Senior Software Engineer - LLM Inference
San Jose or Durham or Mexico City or Vancouver or Bengaluru or Pune or Hoofddorp or Belgrade or Barcelona or Singapore or Sydney or Tokyo
$171k-$257k/yr HybridFull Time
8+ YOE8+ years building distributed, high-performance systems; strong Go/Python, Docker, Kubernetes, CI/CD; knowledge of datacenter, OS internals, virtualization, and ML frameworks.
Docker, Kubernetes, Go, Python, CI/CD, TensorFlow, PyTorch, GPUs
2mo
Save
Mark Applied
Hide
Senior Deep Learning Framework Communications Engineer
Santa Clara or Austin or Westford or Durham or United States
$152k-$288k/yr HybridFull Time
5+ YOE5+ years software engineering experience in HPC/AI, experience with PyTorch/JAX and inference engines, Python/C++/CUDA development, performance benchmarking and profilers, understanding of multi-GPU communication and compilers.
PyTorch, TRT-LLM, vLLM, SGLang, JAX, NCCL, NVSHMEM, GPUDirect, torch.compile, PyTorch profiler, NVIDIA Nsight Systems, Python, C++, CUDA, Triton, cuTe, MPI
2mo
Save
Mark Applied
Hide
Data Science Consultant 2
Charlotte, North Carolina, United States
OnsiteFull Time
Experience building and optimizing LLM inference stacks (vLLM, TensorRT-LLM, Triton), Kubernetes-based serving (KServe, GKE), GPU orchestration, quantization techniques, performance tuning, GCP/Azure, Terraform, observability (Prometheus/Grafana). Bachelor's degree required or equivalent experience; US work authorization required.
vLLM, TensorRT-LLM, Triton, Triton Inference Server, SGLang, SAS, R, Python, Kubernetes, GKE, KServe, Helm, Operators, Terraform, HashiCorp Vault, Prometheus, Grafana, BigQuery, Hadoop, SageMaker, Snowflake, OpenShift (OCP)