Lead AI Inference & Hardware Acceleration Engineer

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

Job summary

Figureai in San Jose, CA, is seeking a Staff AI Inference & Acceleration Engineer to own the on-board inference architecture for humanoid robots. The role involves mapping AI workloads efficiently across compute hardware while driving optimization to meet strict latency and reliability demands.

Successful candidates will have a strong background in hardware acceleration and ML systems, with at least 8 years of industry experience. Key responsibilities include optimizing models and defining inference architectures.

Qualifications

• 8+ years of experience in hardware acceleration and compute architecture.
• Deep understanding of AI/ML inference model formats and deployment pipelines.
• Hands-on experience optimizing embedded hardware models.

Responsibilities

• Own and define the on-board inference architecture for humanoid robots.
• Optimize inference toolchains for target hardware.
• Partner with teams to ensure hardware-friendly model architecture.

Skills

Hardware acceleration

ML systems

C++

Python

AI/ML inference

Computational architecture

Education

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

Tools

TVM

MLIR

TensorRT

Torch

CUDA

Job description

Figureai in San Jose, CA, is seeking a Staff AI Inference & Acceleration Engineer to own the on-board inference architecture for humanoid robots. The role involves mapping AI workloads efficiently across compute hardware while driving optimization to meet strict latency and reliability demands.

Successful candidates will have a strong background in hardware acceleration and ML systems, with at least 8 years of industry experience. Key responsibilities include optimizing models and defining inference architectures.