Robotics Engineer (Perception), SteerAI at Steer AI

About SteerAI

SteerAI is an autonomous mobility technology company powered by VentureOne, the commercialization arm of the Advanced Technology Research Council. SteerAI’s advanced AI-powered autonomy stack, developed by the Technology Innovation Institute, empowers the logistics and defense industries by turning industrial vehicles into autonomous powerhouses that can handle complex off-road missions, transforming operations and protecting organizations' most important assets: their workforce.

Role Overview

We are looking for a Perception Engineer to join our GROUND Robotics team. In this role, you will be primarily responsible for maintaining and evolving the perception module of SteerAI’s CoreX autonomy stack, which supports autonomous mission execution across diverse platforms.

Key Responsibilities

• Maintain and improve CoreX’s perception module, including capabilities such as object detection, semantic segmentation, multi-object tracking, LiDAR-based terrain understanding.
• Extend and adapt the perception system for new robotics platforms and deployment scenarios.
• Develop clean, modular, and efficient C++ code aligned with industry best practices and ROS1/ROS2 standards.
• Collaborate closely with localization, planning, and controls teams to ensure seamless system integration and performance.
• Conduct field testing and iterative tuning of perception features under real-world conditions.
• Contribute to code reviews and maintain detailed technical documentation for system components.

Qualifications

• Bachelor’s or Master's degree in Robotics, Computer Vision, or a related field.
• 4+ years of experience in real-time perception or computer vision systems.
• Strong programming skills in C++, with hands-on experience in ROS1 or ROS2-based systems.
• Proficiency with common perception libraries and frameworks such as OpenCV, PCL, Open3D, PyTorch, and TensorRT.
• Practical experience with sensor calibration, obstacle detection, LiDAR filtering, and related perception tasks.
• Familiarity with multiple sensor modalities including LiDAR, monocular/stereo cameras.
• Experience using modern development tools and workflows (e.g., Git, Docker, Jenkins).
• Exposure to off-road or unstructured terrain perception challenges.
• Familiarity with traditional perception techniques, alongside deep learning-based methods including dataset preparation, model development, and deployment; experience with transformer-based approaches is a plus.
• Hands-on experience with ARM64-based edge devices such as the NVIDIA Jetson family
• Strong communication skills, capable of effectively explaining complex idea.
• Able to work independently and as part of a fast-paced, mission-driven team.
• Proactive mindset with a willingness to pivot between different parts of the perception stack when needed.