Senior/Sr. Staff AI Infrastructure Engineer, Inference & Optimization

What you'll do

• Deploy and optimize vehicle-side AI models, including resource scheduling within embedded constraints.
• Lead system stability, profiling, and root-cause analysis to improve performance and reliability.
• Build scalable serving environments for LLMs and foundational models used in simulation, annotation, and model validation.

What they ask for

• Master’s or higher degree in a related technical field.
• 3-8+ years of industry experience in high-performance computing, AI infrastructure, model optimization, or embedded deployment.
• Strong C++ and Python skills, parallel programming experience with CUDA and OpenMP, and low-level profiling expertise.
• Experience with inference engines and LLM serving frameworks, plus modern GPU architectures and memory bandwidth management.

Nice to have

• Experience optimizing and deploying models on NVIDIA Thor.
• Production experience serving foundation models; experience with PyTorch, quantization, kernel fusion, graph compilation, or real-time AI workloads in vehicles, robotics, or edge devices.

Pay

$169,783 - $351,000 annually (USD), base salary

Tools

C++, Python, CUDA, OpenMP, TensorRT, ONNX Runtime, vLLM, SGLang

AI focus

AI infrastructure for autonomous driving, including vehicle-side inference optimization and cloud-based LLM and foundational-model serving.