Inference Optimization Engineer (Intern)

Inference Optimization Engineer (Intern)

About the Team

We enable Physical AI to operate reliably in the real world. Our mission is to maximize inference efficiency in on-device environments while meeting accuracy and latency requirements under real-world constraints. By understanding the computational structure of VLAs, building dedicated runtime engines, and engineering the software stack from scratch, we shape the next-generation of serving systems.

Responsibilities

•  Analyze the architecture and operations of generative models, especially VLAs

•  Deploy and run models on edge devices, utilizing hardware accelerators such as NPUs

•  Identify performance bottlenecks, then research and apply techniques to resolve them

Minimum Qualifications

•  Proficiency in C/C++ or Python

•  Fundamental CS knowledge and English proficiency to understand ML systems research papers

•  A proactive approach to problem-solving

Preferred Qualifications

•  Experience deploying and optimizing generative models on edge devices

•  Experience profiling performance at kernel and hardware level

•  Kernel programming experience on hardware accelerators such as GPUs or NPUs