Avride
Machine Learning Engineer – Motion Planning & Prediction
About this role
Join an autonomous vehicle team in Austin to build machine learning systems for motion planning and behavioral prediction. You'll design and train deep learning models on massive real-world driving datasets, working across the full ML lifecycle from data processing to real-time vehicle deployment.
What you'll do
- Design, train, and deploy ML models for behavioral prediction and motion planning in autonomous vehicles
- Build data pipelines to process, clean, and label large-scale sensor and simulation datasets
- Develop deep learning architectures (transformers, neural networks) to model complex interactions between traffic agents
- Establish performance metrics and evaluation frameworks that correlate with on-road safety
- Integrate trained models into vehicle embedded systems and optimize for real-time inference
- Research and apply novel ML techniques including imitation learning and reinforcement learning
What they're looking for
- Python
- Deep learning frameworks (PyTorch, TensorFlow, or JAX)
- Neural network architectures and training methodologies
- C++ for high-performance inference
- Machine learning lifecycle management
- Data pipeline development
- Model evaluation and metrics design
- Distributed data processing (preferred)
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Avride
Avride develops autonomous vehicle and delivery robot technology, building the computational infrastructure, data systems, and localization platforms that enable autonomous driving development. The company is hiring backend engineers, ML infrastructure specialists, data platform engineers, robotics software engineers, and site infrastructure engineers to scale its simulation, training, logging, and operational systems.
View all jobs at AvrideLikely interview questions
- Walk us through a machine learning project where you designed and deployed a model end-to-end—what were the key challenges in moving from prototype to production?
- Describe your experience with transformer architectures or other deep learning models for temporal sequence modeling. How would you apply them to predict the behavior of multiple interacting traffic agents?