Computer vision, deep learning, 3D perception, and robotic systems

About the Role

We are a fast-moving robotics startup looking for a talented and hands-on Computer Vision Algorithm Student to join our algorithm team.

You will help develop, test, and improve computer vision and perception algorithms for real robotic systems operating in challenging, dynamic, real-world environments.

The work includes processing images and depth data, detecting and locating objects, evaluating algorithm performance, investigating failure cases, and integrating vision algorithms into a complete robotic system.

This is a great opportunity for a student who enjoys solving practical algorithmic problems, working with real sensor data, and turning computer vision ideas into reliable robotic capabilities.

Responsibilities

• Develop and test computer vision and image-processing algorithms for robotic applications.
• Work on object detection, segmentation, tracking, depth processing, and 3D object localization.
• Process data from RGB and depth cameras and combine it with the robot’s coordinate systems.
• Train, evaluate, and improve deep-learning models.
• Build datasets, analyze annotations, and investigate model errors and edge cases.
• Run experiments on recorded data and real robotic systems.
• Measure algorithm performance and suggest practical improvements.
• Write clean, maintainable, and testable Python code.
• Integrate algorithms into the company’s existing software and robotics infrastructure.
• Work as part of a multidisciplinary team of algorithm, software, robotics, mechanical, and system engineers.

Requirements

• M.Sc. or Ph.D. student in Computer Science, Electrical Engineering, Computer Engineering, Robotics, Data Science, Applied Mathematics, or a related field.
• Availability for at least two working days per week on-site.
• Practical experience in computer vision through academic projects, research, personal projects, or previous employment.
• Strong Python programming skills.
• Experience with OpenCV, NumPy, or similar image-processing libraries.
• Basic understanding of deep learning and convolutional neural networks.
• Experience with at least one deep-learning framework, preferably PyTorch.
• Good understanding of algorithms, linear algebra, geometry, and coordinate transformations.
• Ability to independently investigate technical problems, run experiments, and analyze results.
• Curious, practical, responsible, and comfortable working with noisy real-world data.
• Good communication skills and ability to work in a multidisciplinary team.

Advantages

• Experience with object detection or segmentation models such as YOLO, Mask R-CNN, DETR, or similar models.
• Experience with RGB-D cameras, stereo cameras, point clouds, or 3D geometry.
• Knowledge of camera calibration, pose estimation, projective geometry, or multi-view geometry.
• Experience with object tracking algorithms.
• Experience with ROS or ROS 2.
• Experience integrating algorithms into robotic systems.
• Experience with Linux, Docker, and Git.
• Experience with AWS or other cloud platforms.
• Experience with model training, dataset management, or experiment-tracking tools.
• Familiarity with CUDA, GPU inference, model optimization, or deployment.
• Basic C++ knowledge.
• Experience with simulation environments or synthetic-data generation.
• Relevant GitHub projects, research, competitions, or personal projects.

Location

Jezreel Valley, on

How to Apply

Please send your CV, academic transcript, and any relevant GitHub, project, or research materials.

To: [email protected]