Robotic Vision Engineer - ML & CV

Roboticsconnected

Boston (MA)

On-site

USD 130,000 - 190,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Eka Robotics in Boston is hiring a researcher to advance computer vision for robotic manipulation. You will build vision pipelines, train perception models, and collaborate with robotics engineers to deploy robust perception in real robots.

The role requires a Ph.D. in computer vision or 3+ years in CV, deep learning expertise, and strong Python skills. Experience with PyTorch/Jax and robotics simulators is a plus. This is a hands-on position with real-world impact.

Qualifications

Ph.D. in computer vision or 3+ years of CV experience.
Strong background in machine learning for computer vision, especially deep learning-based perception.
Experience training modern CV models in PyTorch or Jax.
Practical experience with visual representation learning, segmentation, depth estimation, or 3D perception.

Responsibilities

Build computer vision and visual representation learning pipelines for robotic manipulation.
Develop visual models that support reinforcement and imitation learning policies.
Improve data pipelines for vision-based manipulation, including domain randomization and synthetic data generation.
Design and train perception models robust to lighting changes, viewpoint shifts, and occlusion.
Evaluate learned representations on real robotic tasks and iterate on models and data.
Collaborate with robotics and simulation engineers to define perception strategy.