Computer Vision Engineer Intern

About the Role

The Reality Labs Prototyping team builds the physical hardware for Meta's XR and wearables research. This role focuses on integrating computer vision into the lab to:

• Detect defects before parts ship.
• Confirm parts match their CAD models.
• Identify issues on manufacturing machines.
• Provide a live view of the shop floor.

You will collaborate with manufacturing engineers, machinists, and software engineers, with your work impacting real machines and parts.

Key Responsibilities

• Build and train models for detecting anomalies and defects in machined and printed parts from camera images.
• Develop methods to match captured images or 3D scans of physical parts to their source CAD models.
• Prototype camera monitoring for CNC machines and 3D printers to detect errors early.
• Deploy and maintain networked camera systems, managing capture, storage, and the pipeline from camera to model.
• Build tools for generating and augmenting training data, including synthetic images.
• Measure model performance on real lab data and communicate results.

Requirements & Tech Stack

• Python with a deep learning framework such as PyTorch.
• Image processing libraries such as OpenCV.

Qualifications

• Currently pursuing or have a Bachelor's, Master's, or PhD degree in Computer Science, Electrical Engineering, Mechanical Engineering, Mechatronics, Robotics, or a related field.
• Computer vision or deep learning experience from coursework, research, or projects (e.g., detection, segmentation, anomaly detection, pose estimation).
• Intent to return to a degree program after the internship.
• Must obtain and maintain work authorization in the country of employment.

Preferred Qualifications

• 3D vision experience: point clouds, depth cameras, multi-view geometry, or aligning scans to CAD models.
• Experience deploying cameras on a network (IP cameras, RTSP streams, edge devices like NVIDIA Jetson) or running models in real-time.
• Experience generating synthetic training data (e.g., Blender, rendering from CAD, domain randomization).
• Experience with anomaly detection with limited defect examples.
• Projects in industrial inspection, robotics, or machine monitoring.
• Comfortable working across disciplines, including hands-on work on a shop floor.
• Familiarity with CAD tools (e.g., Fusion 360, SolidWorks, NX) and 3D file formats (e.g., STEP, STL).