Computer Vision Engineer
At a glance
Mid-level Machine Learning Engineering role at Tutor Intelligence. Watertown · full-time · $100,000–$300,000 base.
aimlroles summary, based on the employer's posting.
What you'll do
- Set the technical plan and success measures for unclear perception challenges in robot manipulation
- Build and connect vision capabilities such as object detection, segmentation, tracking and pose estimation
- Check camera calibration, coordinate transforms and timing, and catch signs of sensor degradation
- Create repeatable datasets and tests across changes in objects, lighting, viewpoints and occlusion
- Run perception on physical robots, investigate failures, and improve the system using recorded data and experiments
What you bring
- You have independently taken a substantial computer-vision system from an unclear problem to tested integration
- You write strong Python, maintainable software, tests and repeatable experiments
- You can apply camera models, calibration, coordinate frames and 3D geometry in practice
- You can compare geometric vision with learned models and build evaluations that separate real gains from measurement artifacts
Who this fits
This role suits a mid-level engineer who can own perception work and collaborate across research, software, mechanical and electrical engineering. The position is onsite in Watertown.
From the employer
Join us in building generally capable robot workers that see, learn, and act alongside people across the continent.
We believe general-purpose, generally-intelligent robots will be built in our lifetimes. Robots will work in our factories, move our goods, walk on our streets and eventually be in our homes. To build that future, research and deployment must work in lockstep: real-world operation must make the technology better and better technology must make deployment easier. We're looking for the thinkers, builders, and researchers who want to be part of that loop.
As an AI robotics company that deploys its inventions directly into the facilities that need them, on state-of-the-art hardware, every line of code written at Tutor has a direct impact on the global, physical economy.
About the Role
Build perception that makes robot manipulation experiments reliable. You will own a significant vision system from problem definition and data collection through evaluation, integration, and ongoing improvement on physical robots. The work combines camera geometry and learned models, with decisions grounded in measured performance.
You will work closely with research, software, mechanical, and electrical engineers to understand failures across sensing, algorithms, and the robot environment. This role focuses on perception and its integration into manipulation systems.
Responsibilities
- Define the technical approach and success criteria for ambiguous perception problems in robot manipulation.
- Build and integrate capabilities such as detection, segmentation, tracking, object pose estimation, and 3D scene understanding.
- Own camera calibration, coordinate transforms, synchronization assumptions, and checks that expose degraded sensor quality.
- Create reproducible datasets and evaluations covering changes in objects, lighting, viewpoint, and occlusion; prevent evaluation leakage.
- Select and adapt geometric methods and learned models based on accuracy, latency, robustness, and operational constraints.
- Deploy and maintain perception in the robot stack; diagnose failures using recorded data and physical experiments.
- Improve shared evaluation tools and documentation, contribute to design reviews, and mentor colleagues in your domain.
Requirements
- Evidence of independently owning a substantial computer-vision system from an ambiguous problem through tested integration.
- Strong Python engineering and experience writing maintainable code, tests, and reproducible experiments.
- Practical command of camera models, calibration, coordinate frames, and 3D geometry.
- Experience with geometric vision or learned visual models, with the judgment to explain when each approach is appropriate.
- Ability to build representative evaluations, isolate failure modes, and distinguish model improvements from data or measurement artifacts.
- Ability to communicate technical tradeoffs and resolve interfaces with engineers in other disciplines.
Nice to have
- Perception deployed on physical robots, especially manipulation systems.
- Multi-camera or depth systems, sensor fusion, SLAM, or object pose estimation.
- OpenCV, Open3D or PCL; a modern deep-learning framework; C++ or GPU optimization.
- Establish a reproducible baseline, meaningful evaluation, and documented sensing assumptions for an agreed perception problem.
- Deliver a measured improvement that holds up on the physical robot and meets runtime constraints.
- Keep the system diagnosable and usable by colleagues through reliable calibration checks, failure analysis, and documentation.
What Success Looks Like
Our Culture
We believe that something truly special can happen when talented, motivated people work together; at Tutor, every member of our team is empowered to have real impact in everything that they do. We're characterized by both technical excellence and next-level collaboration and respect.
Tutor is an equal opportunity employer and welcomes applicants from all backgrounds. We are committed to providing reasonable accommodations throughout the hiring process — let us know what you need. If you're excited about this role but don't meet every requirement, we still encourage you to apply.