Robot Motion Planning & Prediction - ML Engineer

Avride • Austin, TX

52d • Onsite

About The Position

Avride is an autonomous driving company with the mission to make transportation safer and more efficient through cutting-edge technology. We hold a unique position in the market, developing self-driving taxis and delivery robots. Our delivery robot division already has production in the US and Japan. Our compact team consists of highly talented engineers with extensive expertise. Joining us means diving into a startup atmosphere and making a significant impact on the company's results and the autonomous industry as a whole. We are seeking an ML Engineer to join our robot motion planning team. In this role, you will build and deploy an ML-based motion planning stack that generates socially-aware, real-time trajectories for outdoor delivery robots operating in complex urban environments. This work includes developing closed-loop behavioral models of surrounding agents and training and evaluating a safe ML-based planner on top of this simulation framework to ensure robust and predictable behavior in both simulation and real-world tests.

Requirements

• 3+ years of ML engineering experience or a PhD in a related field.
• Strong Python skills and experience with PyTorch.
• Knowledge of modern C++ and a solid understanding of high-performance code design.
• Solid understanding of machine learning fundamentals and ability to design, train, and evaluate ML models end-to-end — including data preparation, training pipelines, and validation.
• Candidates are required to be authorized to work in the U.S.
• The employer is not offering relocation sponsorship, and remote work options are not available.

Nice To Haves

• PhD in Computer Science, Machine Learning, Robotics, or a related field.
• Experience in ML-based motion planning or related robotics problems.
• Experience with robotics simulation tools or custom data-driven simulators.

Responsibilities

• Develop closed-loop behavioral models of agents using behavioral cloning and related learning techniques.
• Build a simulation framework that uses these models to generate realistic multi-agent interactions.
• Design, train, and evaluate ML-based motion planner that operate safely and efficiently in real-time environments.
• Define evaluation metrics and run large-scale experiments in both simulation and live-ride testing.
• Collaborate with planning, simulation, and perception teams to integrate your models into the full autonomy stack.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: Ph.D. or professional degree
• Number of Employees: 251-500 employees