The posting
Brief Summary
- Join a high-impact engineering team building robust computer vision capabilities for advanced robotic systems used in real-world production environments.
- You will take algorithms from prototyping through deployment, focusing on accuracy, reliability, and real-time performance.
Responsibilities
- Design and develop computer vision algorithms for detection, recognition, tracking, and scene understanding.
- Build and maintain software modules that integrate vision algorithms into robotics platforms with strong performance and reliability.
- Implement and improve 3D perception pipelines, including multi-view geometry, depth estimation, and 3D reconstruction workflows.
- Develop and refine calibration solutions (camera intrinsic, multi-camera, and robot-to-camera) suitable for production use.
- Optimize algorithms and code for runtime efficiency, accuracy, and real-time execution (including GPU acceleration where applicable).
- Prototype new approaches, evaluate feasibility, and move solutions from concept to deployment with cross-functional partners.
- Create test plans and validation methods to ensure stable behavior across varied operating conditions.
- Produce clear technical documentation covering design choices, implementation details, and verification results.
- Stay current with evolving computer vision and machine learning techniques and apply relevant advances to improve solutions.
Requirements
- Master’s or PhD in Computer Science, Electrical Engineering, Robotics, or a related discipline.
- 5+ years of industry experience delivering computer vision solutions in applied, production-facing environments.
- Strong fundamentals in computer vision and image processing (e.g., filtering/denoising, feature/edge-based methods) and applied machine learning for vision systems.
- Hands-on experience with calibration methods and deploying calibration workflows in real systems.
- Proficiency in C++ and Python; experience with CUDA and performance engineering is preferred.
- Practical familiarity with common vision/3D tooling (e.g., OpenCV, point cloud processing libraries) and ML frameworks (e.g., TensorFlow or PyTorch).
- Experience with 3D reconstruction concepts and implementation (e.g., modern neural rendering / 3D representation approaches).
- Strong problem-solving skills, ability to work cross-functionally, and comfort communicating complex technical topics clearly.
By sending us your personal data and curriculum vitae (CV), you are deemed to consent to PERSOL Singapore Pte Ltd ("PERSOL") and its local and overseas subsidiaries and affiliates to collect, use and disclose your personal data to prospective employers/companies based in any country for purposes of evaluating suitability for employment, conducting reference checks, administering employment related services, complying with Government’s health advisories and such other purposes stated in our Privacy Policy.
We may use artificial intelligence ("AI") and machine learning technologies to support our recruitment and placement services, including screening resumes, assessing qualifications and experience, and identifying skills and job matches. Where permitted by applicable law, we may also use such personal data to develop, train, test, improve and/or fine-tune AI and machine learning technologies that support our recruitment and business operations.
For more information on how we collect, use, disclose and protect your personal data, please refer to our Privacy Policy: https://www.persolsingapore.com/policies.If you wish to withdraw your consent, including consent relating to the use of your personal data for AI-enabled recruitment activities and AI development activities, please email us at [email protected].



