Build perception capabilities for detection, classification, tracking, temporal understanding, and 3D vision.
Develop first-person vision and geometric vision systems for factory settings.
Train and debug PyTorch models using synthetic and real-world data, and use field failures to improve models, data, and evaluation.
Optimize low-latency inference and deploy perception systems on NVIDIA Jetson with TensorRT.
Summarised from the posting by AI and can be wrong. The full description is the source.
Requirements
Experience
At least 3 years of experience in computer vision, robotics perception, or applied machine learning, including deploying perception systems beyond notebooks or lab environments
Experience shipping real-time perception systems that work reliably in challenging physical environments
Background in geometric vision, such as calibration, localization, pose estimation, or coordinate transformations
Experience deploying to edge devices or optimizing production inference for low latency
Comfort working directly in field settings and using real-world failures to improve models and data
Experience with synthetic data and Sim2Real (preferred)
Experience with SLAM or VIO (preferred)
Experience with depth estimation or 3D reconstruction (preferred)
Experience with CUDA or TensorRT (preferred)
Experience with ROS2, robot manipulation, or robot learning (preferred)
Skills
Strong Python, PyTorch, and OpenCV skills, with experience building detection, classification, or tracking models
Other requirements
On-site in the United States
Full job description
From Clera’s careers site
ABOUT THE ROLE
Join an early-stage industrial automation team as its first engineer, building computer vision systems that understand manual work in factory settings. You will take perception from experimentation through reliable production deployment, starting with real-time quality inspection.
WHAT YOU'LL DO
Build perception capabilities for detection, classification, tracking, temporal understanding, and 3D vision.
Develop first-person vision systems that handle camera motion, changing viewpoints, occlusion, motion blur, and varied lighting.
Work with the technical leadership team to turn field failures into improved models, data, and evaluation.
Show full descriptionShow less
Build geometric vision systems for calibration, localization, pose estimation, and coordinate transformations.
Train and debug PyTorch models using synthetic and real-world data.
Optimize low-latency inference and deploy systems on NVIDIA Jetson with TensorRT.
Deploy to factory floors and develop reusable perception infrastructure from real-world experience.
WHAT WE'RE LOOKING FOR
At least 3 years of experience in computer vision, robotics perception, or applied machine learning, including deploying perception systems beyond notebooks or lab environments.
Strong Python, PyTorch, and OpenCV skills, with experience building detection, classification, or tracking models.
Experience shipping real-time perception systems that work reliably in challenging physical environments.
Background in geometric vision, such as calibration, localization, pose estimation, or coordinate transformations.
Experience deploying to edge devices or optimizing production inference for low latency.
Comfort working directly in field settings and using real-world failures to improve models and data.
Experience with synthetic data and Sim2Real, SLAM or VIO, depth estimation, 3D reconstruction, CUDA or TensorRT, ROS2, robot manipulation, or robot learning is beneficial.
COMPENSATION & BENEFITS
Base salary is $120,000 to $200,000 annually. Visa sponsorship is available.