Machine Learning Engineer, Perception

This is a fully remote position, open to applicants in Ohio.

📋 Description

• Develop, validate, and enhance machine learning algorithms for tasks related to weld perception, such as point cloud registration, seam detection, and joint geometry estimation.

• Construct and manage data pipelines for the ingestion of annotated 3D scan data, synthetic data generation, and structured dataset administration.

• Conduct model evaluation experiments, perform failure mode analysis, characterize false positive/negative rates, and benchmark against quantitative registration accuracy standards.

• Integrate trained models into production ROS-based robotic services to ensure low-latency inference and compatibility with deployed cells.

• Write clean, well-tested Python code; engage in code and experiment reviews; document methodologies, parameters, and outcomes.

• Lead the research, development, and production deployment of perception algorithms utilizing structured light, RGB, and stereo sensors.

• Design and oversee experiments that evaluate transformer-based and geometric feature learning architectures.

• Create and manage real-time perception systems, including during-weld seam tracking and sensor fusion using probabilistic state estimation techniques such as Kalman filtering.

• Oversee the complete ML lifecycle, from dataset design and annotation strategies to training, benchmarking, and fleet deployment.

• Architect distributed training and hyperparameter optimization workflows; spearhead data acquisition, annotation tools, and strategies for synthetic versus real scan data.

• Mentor engineers at various levels and provide technical leadership in perception systems and machine learning methodologies.

⛳️ 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 substantial production ML experience will also be considered.

• 3+ years of experience for Experienced level or 7+ years for Senior/Staff level in real-world robotics or industrial machine learning.

• Proficient in Python and hands-on experience with PyTorch, including the training, evaluation, and deployment of deep learning models in production environments.

• Experience with 3D point cloud data and libraries such as Open3D, including understanding 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 methods applied to geometric data.

• Comfortable with integrating machine learning models into production robotics services using ROS-based frameworks and containerized deployment environments.

• For Senior/Staff level: Proven experience leading end-to-end ML projects from dataset design to fleet deployment with rigorous go/no-go frameworks; experience in architecting distributed training and hyperparameter optimization workflows.

🏝️ Benefits

• Daily free lunch.

• Flexible PTO.

• Comprehensive medical, dental, and vision coverage.

• 6 weeks of fully paid parental leave, plus an additional 6–8 weeks for birthing parents (totaling 12–14 weeks).

• 401(k) retirement plan through Empower.

• Generous employee referral bonuses.