Machine Learning Engineer, Motion Planning & Prediction
Job Description
Avride seeks a Machine Learning Engineer to join its autonomous vehicle team in Austin, TX (onsite), focusing on motion planning and prediction, building end-to-end ML models, data pipelines, and real-time inference on embedded hardware.
Responsibilities
- Design, train, and deploy advanced ML models for behavioral prediction and motion planning
- Build robust data pipelines to process, clean, and label large-scale vehicle sensor and simulation data
- Leverage transformer-based architectures to model complex temporal interactions among traffic agents
- Define and own model performance metrics, and develop evaluation frameworks aligned with on-road safety and effectiveness
- Collaborate with software engineers to integrate and optimize models for real-time onboard inference on embedded hardware
- Stay current with advances in ML, imitation learning, and reinforcement learning, applying novel techniques to our systems
Requirements
- Proficiency in Python with hands-on experience using modern deep learning frameworks such as PyTorch, TensorFlow, or JAX
- Solid understanding of ML fundamentals, including neural networks, training methodologies, and evaluation techniques
- Experience across the full ML lifecycle—from data exploration and prototyping to deployment and monitoring
- C++ proficiency for high-performance model inference code
Technologies
- Python
- PyTorch
- TensorFlow
- JAX
- C++
- MLflow
- Kubeflow
- Weights & Biases
- Spark
- Ray
Nice to Have
- A strong track record in ML competitions (e.g., Kaggle) or contributions to major open-source ML projects
- Experience applying ML to robotics problems such as behavioral prediction, motion planning, or computer vision
- Experience with MLOps tools and platforms (e.g., MLflow, Kubeflow, Weights & Biases)
- Experience with large-scale distributed data processing and training frameworks (e.g., Spark, Ray)
- Publications in top-tier ML or robotics conferences (e.g., NeurIPS, ICML, CVPR, ICLR, CoRL, RSS)