AI Engineer (Inference System)

Overview

At WIRobotics, we develop a new paradigm of robotic systems by combining deep understanding of physical interaction with AI-driven intelligence. We build large-scale robotic AI models that integrate vision, language, and action, enabling humanoid robots to physically interact with the real world and learn from experience. Our goal is to realize Physical Intelligence—robots with human-level intelligence, manipulation, and adaptive behavior beyond the limits of conventional robotics.

Key Responsibilities

• Design and optimize real-time robot inference pipelines based on system engineering, performance optimization, and deployment experience. Build and operate robust real-time inference pipelines for robotic systems.
  • Design and implement real-time robot inference pipeline architectures
  • Convert and optimize models using TensorRT, ONNX Runtime, and CUDA
  • Improve latency and memory efficiency through quantization, pruning, and mixed-precision techniques
  • Perform profiling-based performance analysis and system debugging
  • Stabilize deployment and operations in edge/embedded environments
  • Collaborate with ML and robotics system teams to optimize end-to-end model–system integration and performance

Qualifications

• Experience in software development and optimization using Python and C++
• Hands-on experience with GPU/NPU-based model inference optimization, including TensorRT, ONNX Runtime, and CUDA
• Experience in model compression, efficiency optimization, and deployment, such as quantization, pruning, and TensorRT/ONNX conversion
• Experience in system architecture design and performance bottleneck analysis, including inference pipeline profiling and latency/memory optimization

Preferred Qualifications

• Senior/Staff-level experience in system engineering
• Experience with ROS/ROS2, embedded systems, and real-time systems
• Experience applying robotics inference in real-world systems (preferred but not required)

How to Apply

Email: recruit@wirobotics.com Documents: Resume, Portfolio (optional) Deadline: Open until filled