Key skills
AIMachine LearningMLPyTorchTensorFlowKubernetesK8s
About this role
Vertex Elite LLC is currently seeking a qualified Performance Engineer to join their team. The role focuses on AI/ML performance engineering, requiring expertise in HPC, GPU optimization, and advanced machine learning tools.
Responsibilities:
- AI/ML Performance Engineering: 5+ years in HPC, large-scale inference, and GPU optimization
- Background: CS/STEM degree (or equivalent)
- ML Tools: Advanced PyTorch/TensorFlow optimization, modern ML architectures
- CUDA: Expert-level CUDA programming and GPU kernel optimization
- GPU Knowledge: In-depth knowledge of GPU architecture, memory hierarchy, and cache optimization
- Infrastructure: NVIDIA Triton, Apache Ray, Kubernetes (K8s) orchestration
- Acceleration: RAPIDS, GPU-accelerated data pipelines
- Profiling: Benchmarking, Nsight profiling, performance monitoring
- Track Record: Proven success in large-scale AI system performance tuning
Requirements:
- 5+ years in HPC, large-scale inference, and GPU optimization
- CS/STEM degree (or equivalent)
- Advanced PyTorch/TensorFlow optimization, modern ML architectures
- Expert-level CUDA programming and GPU kernel optimization
- In-depth knowledge of GPU architecture, memory hierarchy, and cache optimization
- NVIDIA Triton, Apache Ray, Kubernetes (K8s) orchestration
- RAPIDS, GPU-accelerated data pipelines
- Benchmarking, Nsight profiling, performance monitoring
- Proven success in large-scale AI system performance tuning