> Markdown version of [/jobs/ext/4783713-machine-learning-engineer-robotics](https://www.wearedevelopers.com/jobs/ext/4783713-machine-learning-engineer-robotics). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Machine Learning Engineer, Robotics - **Company:** Path Robotics - **Location:** Columbus, OH, United States (Remote available) - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, C++ (Programming Language), Nvidia CUDA, Information Theory, Python (Programming Language), Kinematics, Machine Learning, Motion Planning, Reliability Engineering, Reinforcement Learning, Pytorch, Transfer Learning, Deep Learning, Information Technology, ONNX (Open Neural Network Exchange) Format, Machine Learning Operations, TensorRT - **Published:** November 19, 2026 - **Apply:** https://www.careerbuilder.com/job-details/machine-learning-engineer-robotics-columbus-oh--4164a7ab-f9f7-4665-a69b-a0c890383065 ## About the Role Machine Learning, Robotics, Risk, Robotics, Continuous Improvement, Artificial Intelligence (AI), Reliability Engineering, Vehicle Fleets, Machine Learning, Data Modeling, * An MS or PhD in Computer Science, Robotics, Machine Learning, or a related field. * 2+ years of applied machine learning for robotics or autonomy, in research or industry. * Fluent in Python with PyTorch or JAX, and experienced training, evaluating, and deploying deep learning models. * Strong foundations in linear algebra, 3D geometry, kinematics, and optimization. * You've run your methods on real robot hardware. * You explain model results and their limits clearly, so planning, perception, and field teams know when to trust them. Preferred * C++, and experience deploying models into a C++ or ROS 2 production stack. * Motion planning, trajectory optimization, or collision checking. * Active perception, next-best-view or informative path planning, or 3D point cloud learning. * Uncertainty estimation and calibration, or Bayesian and information-theoretic planning. * GPU inference optimization (CUDA, TensorRT, ONNX). * Simulation and sim-to-real transfer (Isaac Lab, MuJoCo). * Publications at RSS, CoRL, ICRA, IROS, NeurIPS, ICML, or similar venues. ## Description * Train models that work with classical methods, such as initial guesses and learned costs for trajectory optimization, plan quality and feasibility predictors, and learned collision models. * Develop viewpoint planning policies that choose where and how to scan, and predict scan quality before the robot commits. * Apply imitation learning, reinforcement learning, and generative models such as diffusion and flow matching where they outperform classical baselines. * Build production ML pipelines: datasets from fleet logs and simulation, training, and metrics. * Evaluate models in the loop, with offline metrics that predict gains on the robot, failure-mode analysis, and calibrated confidence that determines when the system falls back to classical methods. * Own your models end to end, from prototype to deployment on live robotic cells, with low-latency inference and monitoring., * Daily free lunch to keep you fueled and connected with the team