Staff AI Inference and Acceleration Engineer

What you'll do

• Map and partition inference workloads across accelerators; define system-level compute budgets and evaluate future hardware.
• Optimize inference toolchains, models, kernels, scheduling, memory layout, and data movement; profile and eliminate bottlenecks.
• Collaborate with AI/ML and platform teams on hardware-friendly models, runtime integration, scheduling, and power management.

What they ask for

• M.S. or Ph.D. in Computer Engineering, Electrical Engineering, Computer Science, or a related field — or equivalent industry experience.
• Deep understanding of AI/ML inference, including model formats, runtimes, and deployment pipelines.
• Hands-on edge or embedded model optimization experience using quantization, pruning, and operator-level tuning; strong computer architecture understanding.
• Experience profiling and benchmarking inference across CPU, GPU, NPU, DSP; solid C++ and Python skills.

Nice to have

• Knowledge of real-time operating constraints and their impact on inference scheduling.
• Track record of co-designing model architectures with ML teams to meet hardware constraints.

Pay

$180,000 to $275,000 per year (base salary)

Tools

NPU, GPU, DSP, CPU, ONNX, TFLite, TVM, MLIR

AI focus

Optimize and deploy AI/ML inference on humanoid robot hardware, including workload mapping, compression, runtime execution, and hardware-aware model design.