Machine Learning / Computer Vision Engineer

The role

This person will build computer vision and visual representation learning pipelines for robotic manipulation. They will develop visual models for reinforcement learning and imitation learning policies and improve data pipelines.

What you will do

• Build computer vision and visual representation learning pipelines for robotic manipulation
• Develop visual models that support reinforcement learning and imitation learning policies
• Improve data pipeline for vision-based manipulation policies
• Design and train perception models robust to environmental variations
• Evaluate learned visual representations and policies on real robotic manipulation tasks
• Collaborate with robotics, robot learning, and simulation engineers
• Set up, calibrate, and evaluate camera and depth sensing systems

Required qualifications

• Ph.D. in computer vision or 3+ years of experience working on a computer vision product
• Strong background in machine learning for computer vision, especially deep learning-based visual perception
• Experience training modern computer vision models in Jax, PyTorch or similar frameworks
• Practical experience with visual representation learning, object detection, segmentation, pose estimation, depth estimation, tracking, or 3D perception
• Strong Python programming skills
• Ability to move fluidly between research code and production-quality systems
• Strong understanding of how data distribution, sensor noise, calibration, lighting, and scene variation affect model performance

Nice to have

• Experience training policies from visual observations, including RGB, RGB-D, point clouds, object-centric representations, or learned latent representations
• Experience with domain randomization, synthetic data generation, differentiable rendering, neural rendering, or photorealistic simulation
• Experience with robotics simulators or synthetic data tools such as Isaac Sim, MuJoCo or similar environments
• Familiarity with robot learning methods such as reinforcement learning, behavior cloning, diffusion policies, offline RL, or learning from demonstrations
• Experience with real robot deployment, including camera calibration, hand-eye calibration, depth sensors, ROS/ROS2, or robot data collection pipelines
• First-author publications in top computer vision, robotics, or machine learning venues such as CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, RSS, CoRL, ICRA, or IROS

About the company

Eka Robotics is on a mission to build intelligence for the physical world - robots that are fast, general, and reliable. Their team consists of pioneers in robotics and machine learning.