Machine Learning Engineer, Perception

This role focuses on weld perception for embodied robotics at Path Robotics, with responsibilities spanning model development, evaluation, and deployment of computer vision and deep learning systems for 3D sensing.

Location

Columbus, OH (onsite)

Role Overview

As a Machine Learning Engineer, you will implement and deploy machine learning algorithms for weld perception tasks, including point cloud registration, seam detection, and joint geometry estimation. By level, the scope expands toward broader coverage of joint types and part geometries, along with increased leadership across research, development, and production deployment.

Responsibilities

• Implement, validate, and iterate on machine learning algorithms for weld perception tasks, including point cloud registration, seam detection, and joint geometry estimation, progressively expanding coverage across joint types and part geometries.
• Build and maintain data pipelines for training and evaluating perception models, including ingestion of annotated 3D scan data, synthetic data generation, and structured dataset management to support iterative improvements.
• Run rigorous model evaluation experiments, including failure mode analysis, FP/FN rate characterization, and benchmarking against quantitative registration accuracy thresholds, and communicate findings to guide next steps.
• Integrate trained models into production ROS-based robotics services, ensuring low-latency inference and compatibility with deployed cell configurations.
• Write clean, well-tested Python code; participate in code and experiment reviews; and maintain clear documentation of methods, parameters, and results.
• Lead research, development, and production deployment of advanced perception algorithms across point cloud registration, seam detection, and real-time in-process tracking for structured light, RGB, and stereo sensors.
• Design and lead experiments evaluating state-of-the-art deep learning models, including transformer-based and geometric feature learning architectures.
• Design and lead real-time perception systems such as during-weld seam tracking, using sensor fusion with probabilistic state estimation (for example, Kalman filtering) to support robust weld performance.
• Define and own the end-to-end ML lifecycle, from dataset design and annotation strategy through training, benchmarking, and fleet deployment, supported by clear go/no-go evaluation frameworks.
• Architect distributed training and hyperparameter optimization workflows, and drive strategy for data acquisition, annotation tooling, and synthetic versus real scan data usage.
• Mentor engineers across levels by providing technical leadership on perception systems and ML methodology.

Requirements

• Master’s or Ph.D. in Computer Science, Robotics, or a related field (Computer Vision, ML, or Perception); Bachelor’s with strong production ML experience also considered.
• Experienced: 3+ years in real-world robotics or industrial ML. Senior/Staff: 7+ years in real-world robotics or industrial ML.
• Strong Python fluency and hands-on PyTorch experience, including training, evaluating, and deploying deep learning models in production.
• Experience with 3D point cloud data and libraries such as Open3D, including geometric concepts like surface segmentation, spatial queries, and point-wise labeling.
• Familiarity with 3D deep learning architectures such as PointNet++, GeoTransformer, or similar transformer-based or graph-based approaches on geometric data.
• Comfort integrating ML models into production robotics services within ROS-based architectures and containerized deployment environments.
• Senior/Staff: Demonstrated track record leading end-to-end ML projects from dataset design through fleet deployment using rigorous go/no-go frameworks, plus experience architecting distributed training and hyperparameter optimization workflows.

Technologies

• Python
• PyTorch
• Open3D
• ROS
• Kalman filtering
• PointNet++
• GeoTransformer
• Transformer-based architectures
• Graph-based approaches
• Containerized deployment environments
• Structured light
• RGB
• Stereo sensors

Benefits

• Daily free lunch to keep you fueled and connected with the team
• Flexible PTO so you can take the time you need, when you need it
• Comprehensive medical, dental, and vision coverage
• 6 weeks fully paid parental leave, plus an additional 6–8 weeks for birthing parents (12–14 weeks total)
• 401(k) retirement plan through Empower
• Generous employee referral bonuses