Inference Optimization Engineer

About the Team

WoRV builds Physical AI that understands and acts in the real world. The Machine Learning Engineering (MLE) team at WoRV is responsible for bringing advanced models out of the lab onto physical robots and vehicles, optimizing them to run within tight resource constraints.

We are hiring research engineers to join us in building the software stack from the bottom up to shape the next generation of serving systems for Physical AI.

Responsibilities

• Analyze the computational workloads of emerging VLA/WAM architectures, leveraging performance profiling and analytical modeling to identify bottlenecks.

• Design hardware-aware model compression and acceleration algorithms, exploring techniques such as quantization, distillation, and architecture-specific optimizations to reduce computational complexity, memory footprint, and inference latency.

• Implement high-performance kernels/operators for specialized AI accelerators, leveraging hardware-specific optimizations including efficient memory access patterns and kernel fusion to maximize computational efficiency.

• Design dedicated runtime engines, integrating efficient memory management and kernel execution scheduling to enable real-time inference on resource-constrained hardware platforms.

Minimum Qualifications

• A proactive approach to problem-solving: Find the problem, dig into it, and drive it to resolution

• Proficiency in C/C++ or Python

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

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