ML Engineer, Motion Planning & Prediction for AVs

Top Echelon Software, LLC; Austin (TX); On-site; USD 120,000 - 170,000; Full time

Benefits offered by this job

Healthcare

Commuter benefits

FSA

Disability and life insurance

401(k)

Generous PTO

Lunches

Job summary

Top Echelon Software, LLC is seeking a Machine Learning Engineer for motion planning and prediction in autonomous mobility. You will design and deploy deep learning models focused on behavioral prediction and real-time inference on embedded hardware, collaborating across engineering teams to enable safe navigation in complex environments.

The role requires strong Python skills and hands-on experience with PyTorch, TensorFlow, or JAX, plus proficiency in C++ for high-performance inference.

Qualifications

• Strong Python and DL framework experience (PyTorch, TensorFlow, or JAX).
• Experience with full ML lifecycle from data exploration to deployment.
• Proficiency in C++ for high-performance inference.

Responsibilities

• Design, train, and deploy state-of-the-art ML models for behavioral prediction and motion planning.
• Develop robust data pipelines to process, clean, and label massive-scale sensor data.
• Work with transformers to model temporal interactions between traffic agents.
• Establish and own metrics for model performance and safety.
• Collaborate with software engineers to optimize models for real-time vehicle inference.
• Stay current with ML/robotics research and apply novel techniques.

Skills

Python

C++

PyTorch

TensorFlow

JAX

Tools

MLflow

Kubeflow

Weights & Biases

Spark

Ray

Job description

Top Echelon Software, LLC is seeking a Machine Learning Engineer for motion planning and prediction in autonomous mobility. You will design and deploy deep learning models focused on behavioral prediction and real-time inference on embedded hardware, collaborating across engineering teams to enable safe navigation in complex environments.

The role requires strong Python skills and hands-on experience with PyTorch, TensorFlow, or JAX, plus proficiency in C++ for high-performance inference.