Staff AI Inference & Acceleration Architect

Figure; San Jose (CA); On-site; USD 180,000 - 275,000; Full time

Job summary

Figure is seeking a Staff AI Inference & Acceleration Engineer in San Jose, CA, to lead the on-board inference architecture for humanoid robots. Candidates should have extensive experience in AI/ML inference and strong software engineering skills in C++ and Python.

This role involves optimizing models for low-power performance and ensuring real-time execution across various compute hardware. The position offers a competitive salary between $180,000 and $275,000 annually.

Qualifications

• 8+ years of industry experience in hardware acceleration, ML systems, or compute architecture.
• Hands-on experience optimizing models for edge or embedded hardware.
• Solid software engineering skills in C++ and Python.

Responsibilities

• Own the on-board inference architecture for humanoid robots.
• Optimize inference toolchains end-to-end for target hardware.
• Profile inference pipelines to eliminate bottlenecks.

Skills

AI/ML inference

Hardware acceleration

C++

Python

Computer architecture

Software engineering

Education

M.S. or Ph.D. in Computer Engineering, Electrical Engineering, or Computer Science

Tools

TVM

MLIR

TensorRT

Torch

CUDA

Job description

Figure is seeking a Staff AI Inference & Acceleration Engineer in San Jose, CA, to lead the on-board inference architecture for humanoid robots. Candidates should have extensive experience in AI/ML inference and strong software engineering skills in C++ and Python.

This role involves optimizing models for low-power performance and ensuring real-time execution across various compute hardware. The position offers a competitive salary between $180,000 and $275,000 annually.