Senior Deep Learning Engineer
Core
Optimizing and deploying NVIDIA Cosmos World Foundation Models for high-performance inference on diverse GPU platforms to accelerate physical AI development for autonomous vehicles, robots, and video analytics.
Role type
Senior Deep Learning Engineer (Systems & Inference)
Builds
Production-grade inference systems for physical AI models (Cosmos WFMs)
Domain
AI/ML, GPU Systems, Autonomous Vehicles, Robotics
Deliverable
production ML models
Required skills
Deep Learning, Python, PyTorch, Inference Optimization, Quantization, TensorRT, CUDA
Preferred skills
Triton Inference Server, Docker, Diffusion Models, GPU Workload Tuning
Technologies
PyTorch, TensorRT, TensorRT-LLM, vLLM, SGLang, CUDA, Docker, Triton Inference Server
Responsibilities
Improve inference speed for Cosmos WFMs on GPU platforms, Carry out production deployment of Cosmos WFMs, Profile and analyze deep learning workloads to identify and remove bottlenecks
Seniority
Senior, hands-on IC