Senior / Staff AI Research Engineer, Real-Time Inference

Skills

About the Role

You will build and optimize inference pipelines for embodied AI models such as VLA, perception and world models on edge hardware like NVIDIA Jetson. You will write CUDA-level optimizations, apply quantization, pruning and distillation, profile stacks with NSight, TensorRT and Triton, collaborate with ML and robotics teams, and establish benchmarking frameworks.

Requirements

• Master's degree in Computer Science, Electrical Engineering or related field with 4+ years of experience, or a PhD
• Deep expertise in CUDA programming, GPU architecture and kernel optimization
• Hands-on experience with model quantization, pruning, distillation and deployment using TensorRT, ONNX Runtime, TVM or Triton
• Proficiency in C++ and Python; systems programming and profiling skills
• Experience deploying ML models on edge or embedded hardware
• 5 days/week in-office

Responsibilities

• Develop and optimize inference pipelines for embodied AI models on edge hardware such as NVIDIA Jetson
• Implement CUDA-level optimizations including custom kernels, memory layout tuning and graph compilation
• Apply model compression techniques including quantization, pruning, distillation and structured sparsity
• Profile and debug inference stacks using NSight, TensorRT and Triton
• Collaborate with ML research and robotics teams to co-design model architectures
• Establish benchmarking frameworks for latency, throughput, power and accuracy

Benefits

• Competitive stock options/equity programs
• Health, dental, and vision insurance
• 401(k) plan
• Visa sponsorship and green card support for qualified candidates
• Lunches and dinners, fully stocked kitchen, team-building events