Inference Engineer (Robotics)

TL;DR

Inference Engineer (Robotics): Optimizing model serving efficiency and GPU inference performance for general-purpose robotics research with an accent on kernel-level optimizations and data movement. Focus on building scalable serving infrastructure and designing inference-friendly models for real-world multimodal workloads.

Location: Hybrid (San Francisco, CA). Must be based in or be able to relocate to the US.

Company

An AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Improve model serving, inference performance, and overall system efficiency.
• Optimize kernels and data movement to increase system throughput and reliability.
• Collaborate with research and product teams to scale models effectively.
• Develop and maintain critical serving infrastructure to support robotics growth.

Requirements

• Deep expertise in model performance optimization at the inference layer.
• Strong background in kernel-level systems and low-level performance tuning.
• Experience scaling AI systems for real-world multimodal workloads.
• Ability to navigate ambiguity and drive complex technical initiatives.
• Must be based in or be able to relocate to San Francisco, CA.

Culture & Benefits

• Hybrid work model with 3 days per week in the office.
• Relocation assistance provided for new employees.
• Work on cutting-edge AGI-level intelligence in dynamic, real-world settings.
• Inclusive environment with a strong commitment to equal opportunity.