Founding Engineer, Computer Vision & Robotics
Summary
First engineer at an early-stage industrial automation startup building computer vision systems that understand manual factory work. Day to day: build detection, tracking, and 3D/geometric perception, train PyTorch models on synthetic and real data, and optimize edge inference (NVIDIA Jetson/TensorRT) for quality inspection deployed on factory floors.
About the Role
Join an early-stage industrial automation team as its first engineer, building computer vision systems that understand manual work in factories. You will take perception from experimental models to reliable quality inspection systems deployed in real production environments, with potential to extend into robotic learning over time.
What You'll Do
Build detection, classification, tracking, temporal understanding, and 3D vision capabilities for real-world perception.
Address first-person vision challenges such as camera motion, changing viewpoints, occlusion, motion blur, and variable lighting.
Work with the technical lead to use deployment failures to improve models, data, and evaluation.
Develop geometric vision systems for calibration, localization, pose estimation, and coordinate transformations.
Train and debug PyTorch models using synthetic and real-world data.
Optimize and deploy low-latency inference on NVIDIA Jetson and TensorRT.
Deploy systems on factory floors and turn field learnings into reusable perception infrastructure.
What We're Looking For
At least 3 years of experience building and deploying computer vision, robotics perception, or applied machine learning systems beyond notebooks or lab environments.
Strong Python, PyTorch, and OpenCV skills, with experience shipping real-time systems in changing physical-world conditions.
Experience building detection, classification, or tracking models and geometric vision systems.
Experience owning an open-ended physical-world problem end to end and working directly with users or in field deployments.
Experience deploying on edge devices or optimizing inference for production latency.
Experience with synthetic data and Sim2Real, SLAM or VIO, depth estimation, 3D reconstruction, CUDA, TensorRT, ROS2, robot manipulation, or robot learning is beneficial.
Compensation & Benefits
Base salary: $150,000 to $200,000 annually. Visa sponsorship is available.
Location
On-site in the United States.
Skills
As published by ashby · 2 questions
Basics
Name, Email, Resume
Short answers (1)
Pick from a list (1)
- Do you have work authorization to work in that country?
