Founding Engineer, Computer Vision & Robotics
At a glance
Mid-level Machine Learning Engineering role at Clera. United States · full-time · $150,000–$200,000 base.
aimlroles summary, based on the employer's posting.
What you'll do
- Build vision systems that detect, classify and track activity, interpret events over time, and understand factory scenes in 3D
- Make first-person camera systems work through movement, blocked views, blur and changing light
- Use deployment failures to improve models, datasets and evaluation with technical leaders
- Develop calibration, localization, pose estimation and coordinate-conversion capabilities
- Train and troubleshoot PyTorch models, speed up edge inference, then deploy systems and reusable tools on factory floors
What you bring
- At least three years building and deploying computer vision, robotics perception or applied machine-learning systems beyond lab settings
- Strong Python, PyTorch and OpenCV skills, including hands-on work with detection, classification or tracking models
- Experience delivering real-time perception that handles changing light, occlusion, blur or camera movement
- Background in geometric vision and taking an open-ended physical-world problem from start to finish
Who this fits
This suits a mid-level engineer who wants to be the first engineer on a founding team and build perception systems from experiments through factory deployment. The role is on-site in the United States and includes work on factory floors. Visa sponsorship is available.
From the employer
About the Role
Join the founding team of an industrial automation startup as its first engineer, building computer vision systems for manufacturing quality inspection. You will take perception technology from experiments to reliable deployments on factory floors, helping detect process errors early and laying groundwork for future robotic automation.
What You'll Do
Build perception systems for detection, classification, tracking, temporal understanding, and 3D vision in real-world factory conditions.
Address first-person camera challenges such as camera motion, changing viewpoints, occlusion, motion blur, and varying lighting.
Work with the technical leadership team to turn deployment failures into improvements to models, data, and evaluation.
Build geometric vision capabilities including calibration, localization, pose estimation, and coordinate transformations.
Train and debug PyTorch models on synthetic and real-world data, and optimize low-latency inference for edge deployment.
Deploy systems on factory floors and develop reusable perception infrastructure from field learnings.
What We're Looking For
At least 3 years of experience in computer vision, robotics perception, or applied machine learning, including building and deploying perception systems beyond notebooks or lab environments.
Strong Python, PyTorch, and OpenCV skills, with experience building and debugging detection, classification, or tracking models.
Experience shipping real-time perception systems that perform reliably amid changing lighting, occlusion, motion blur, or camera motion.
Experience with geometric vision and ownership of an underspecified physical-world problem from end to end.
Experience deploying on edge devices or optimizing production inference, and working directly with users or in field deployments.
Experience with synthetic data and Sim2Real, SLAM or VIO, depth or 3D reconstruction, CUDA or TensorRT, ROS2, or robot learning is beneficial.
Compensation & Benefits
Base salary is $150,000 to $200,000 USD annually. Visa sponsorship is available.
Location
On-site in the United States, with factory-floor deployments.