Clera

Computer Vision & Robotics Intern

San Francisco. Posted 8 days ago

The role

You will build and improve vision pipelines for detection, classification, tracking, and temporal understanding. You will work on perception systems to detect process deviations in factory environments.

What you will do

  • Build and improve vision pipelines for detection, classification, tracking, and temporal understanding.
  • Test first-person perception in the presence of camera motion, changing viewpoints, occlusion, motion blur, and variable lighting.
  • Use synthetic and real-world data to find failure cases and improve model performance.
  • Train, evaluate, and debug PyTorch vision models.
  • Explore geometric vision, calibration, localization, pose estimation, and 3D perception.
  • Optimize models for low-latency inference and edge deployment.
  • Build evaluation tools and experiments to measure performance in real-world conditions.
  • Support factory deployments and assess system performance on the shop floor.

Required qualifications

  • Currently studying computer science, robotics, electrical engineering, mechanical engineering, or a related field
  • Interest in computer vision and physical AI
  • Comfort with Python
  • Hands-on experience in computer vision, machine learning, or robotics
  • Hands-on robotics experience
  • A computer vision, robotics, or perception project using real sensor or camera data
  • Ability to learn quickly, debug technical problems, build projects, and take ownership

Nice to have

  • Experience with PyTorch
  • Experience with OpenCV
  • Experience with object detection
  • Experience with tracking
  • Experience with synthetic data
  • Experience with SLAM or visual-inertial odometry
  • Experience with 3D vision
  • Experience with CUDA or TensorRT
  • Experience with ROS 2
  • Experience with NVIDIA Jetson

Benefits

  • Visa sponsorship is available
  • Support for relocation from Germany

About the company

clera is an early-stage industrial automation team building computer vision systems to understand and verify manual assembly work.