System Integration Engineer - Foundation Model Team
Full-time /Part-time /Contract (English)Job Overview
Telexistence develops remote controlled robots with artificial intelligence, with the mission to change robots, change the structure, and change the world. Gathered by high expertise professionals from all over the world, the engineering team consistently develops robotic hardware, software and AI technology in-house. TX aims to expand the scope of robotics activities beyond the factory floor and transform the fundamental nature of labor society.
Position Summary
As the Robotics System Integration Engineer at Foundation Model Team, you will deploy large-scale multimodal models that integrate VLA (vision, language, and action) components for real-world robotic manipulator applications. To train the VLA models, you will develop an automated data collection pipeline via teleoperation and augment the collected datasets using simulators—beyond lab-scale or proof-of-concept demos.
Telexistence develops remote controlled robots with artificial intelligence, with the mission to change robots, change the structure, and change the world. Gathered by high expertise professionals from all over the world, the engineering team consistently develops robotic hardware, software and AI technology in-house. TX aims to expand the scope of robotics activities beyond the factory floor and transform the fundamental nature of labor society.
Position Summary
As the Robotics System Integration Engineer at Foundation Model Team, you will deploy large-scale multimodal models that integrate VLA (vision, language, and action) components for real-world robotic manipulator applications. To train the VLA models, you will develop an automated data collection pipeline via teleoperation and augment the collected datasets using simulators—beyond lab-scale or proof-of-concept demos.
Key Responsibilities
- Integrating robotic controller
- Implement our robotics controller & state machine & data collection ROS1/ROS2 node for bridging deep learning inference.
- Work hand-in-hand with software, hardware teams and site operators to diagnose issues and optimize inference for new or unexpected scenarios in the real market.
- Optimizing trained policies (e.g: TensorRT, ONNX) onto embedded compute platforms (NVIDIA Jetson or similar)
- Physics Photorealistic Simulator
- Bridging the simulator by ROS1/ROS2 for evaluating the trained inference node in the physics simulator
- Augment automatically collected real datasets by leveraging photorealistic simulators.
- Overcome the sim2real gap, such as actuator hardware & photorealistic camera parameters
Qualifications
- Technical Skills
- 3+ years of experience in modern C++ (C++14 or above) and python
- Proficiency using ROS1/2 and embedded edge hardware (e.g., Jetson).
- Strong background in robot control with demonstrated ability to handle complex, multi-degree-of-freedom robots by considering safety, reliability and performance.
- Experience with photorealistic physics simulators for robots (e.g., Isaac Sim)
- Proficiency for URDF and USD format for physics simulator
- Soft Skills & Culture Fit
- Comfortable in a performance-driven environment (high rewards for results, potential demotion for underperformance).
- Communication skills in English; Japanese proficiency is a plus.
Position Location will be at Telexistence's Headquarters Office (Heiwajima, Tokyo) or another location designated by the company.
The role assignment may be modified based on organizational requirements. This could include changes to your job responsibilities, reporting structure, or team assignment.