Machine Learning Engineer, Perception

Path Robotics • Columbus, OH

5d

About The Position

Path Robotics is hiring Machine Learning Engineers for experienced (L3/L4), senior (L5), and staff (L6) openings at the intersection of welding science and artificial intelligence. The role applies problem solving, computer vision, deep learning, and Python programming to perception challenges in robotics.

Experienced engineers implement, validate, and improve machine learning algorithms for weld perception, including point cloud registration, seam detection, and joint geometry estimation. They build data pipelines using annotated 3D scans, synthetic data, and structured datasets; conduct rigorous model evaluations and failure analyses; integrate trained models into production ROS-based robotics services; and write, test, review, and document code and experiments.

Senior and staff engineers lead development and production deployment of perception algorithms across structured-light, RGB, and stereo sensors. They design experiments for advanced deep learning models and real-time perception systems, including during-weld seam tracking and sensor fusion. They own the end-to-end ML lifecycle, architect distributed training and hyperparameter-optimization workflows, guide data acquisition and annotation strategy, and mentor engineers.

Requirements

• Master's or Ph.D. in computer science, robotics, or a related field such as computer vision, machine learning, or perception; a bachelor's degree with strong production ML experience is also considered.
• At least 3 years of experience for experienced-level roles or 7 years for senior/staff roles in real-world robotics or industrial machine learning.
• 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 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.
• Ability to integrate ML models into production robotics services within ROS-based architectures and containerized deployment environments.
• For senior/staff roles, demonstrated leadership of end-to-end ML projects from dataset design through fleet deployment using rigorous go/no-go frameworks.
• For senior/staff roles, experience architecting distributed training and hyperparameter-optimization workflows.

Responsibilities

• Implement, validate, and iterate on machine learning algorithms for weld perception, including point cloud registration, seam detection, and joint geometry estimation.
• Build and maintain training and evaluation data pipelines using annotated 3D scan data, synthetic data generation, and structured dataset management.
• Run model evaluation experiments, analyze failure modes, characterize false-positive and false-negative rates, and benchmark registration accuracy against quantitative thresholds.
• Communicate evaluation findings to guide next steps.
• Integrate trained models into production ROS-based robotics services, with low-latency inference and compatibility with deployed cell configurations.
• Write clean, well-tested Python code; participate in code and experiment reviews; and document methods, parameters, and results.
• For senior/staff roles, lead research, development, and production deployment of perception algorithms across point cloud registration, seam detection, and real-time in-process tracking using 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, including during-weld seam tracking and sensor fusion with probabilistic state estimation such as Kalman filtering.
• Own the end-to-end ML lifecycle, from dataset design and annotation strategy through training, benchmarking, and fleet deployment, with go/no-go evaluation frameworks.
• Architect distributed training and hyperparameter-optimization workflows; drive strategies for data acquisition, annotation tooling, and synthetic versus real scan data.
• Mentor engineers across levels and provide technical leadership on perception systems and ML methodology.

Benefits

• Daily free lunch.
• Flexible paid time off.
• Medical, dental, and vision coverage.
• Six weeks of fully paid parental leave, plus an additional 6–8 weeks for birthing parents (12–14 weeks total).
• 401(k) retirement plan through Empower.
• Employee referral bonuses.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level