Senior/Sr. Staff AI Infrastructure Engineer, Inference & Optimization
Core
Lead performance tuning, deployment, and resource scheduling of cutting-edge AI models across on-vehicle and cloud infrastructure to ensure ultra-low latency and operational reliability.
Role type
Senior/Sr. Staff AI Infrastructure Engineer (Inference & Optimization)
Builds
High-efficiency inference pipelines, system-level stability frameworks, and service-oriented deployment environments for LLMs and foundational models.
Domain
Autonomous driving, high-performance computing, AI infrastructure
Deliverable
production ML models
Required skills
C++, Python, CUDA, OpenMP, TensorRT, ONNX Runtime, vLLM, SGLang, TensorRT-LLM, GPU architecture optimization, system profiling, quantization, kernel fusion
Preferred skills
NVIDIA Thor platform optimization, large foundation model serving (LLaMA, Qwen, GPT), PyTorch, model quantization (INT8/FP8/AWQ), real-time AI workloads in autonomous vehicles
Technologies
CUDA, OpenMP, TensorRT, ONNX Runtime, vLLM, SGLang, TensorRT-LLM, NVIDIA Hopper, NVIDIA Thor, PyTorch
Responsibilities
Own deployment and optimization of vehicle-side AI models; Lead vehicle-side system stability initiatives; Architect and scale service-oriented deployment environments for LLMs; Track and evaluate industry methodologies and optimization toolchains; Establish system-level profiling and telemetry frameworks; Collaborate cross-functionally with Perception, Cloud Infrastructure, and Safety teams.
Seniority
Senior/Sr. Staff, hands-on IC with technical leadership