Machine Learning Engineer, Software

Before the detail, here's the challenge you'd help us solve. We build the embodied intelligence that moves real vehicles safely, and the ecosystem a billion machines will run on in the future. Very few people in AI can say this. Every role here, whatever the team, plugs into that. Here’s what this particular role covers.

Our Application Software team pushes the frontier of model-based autonomous driving, improving core driving performance and developing intelligent features such as personalisation, comfort and collaboration. As a Machine Learning Engineer, you’ll lead critical initiatives to design and deliver ML-driven behaviours that scale from assisted to autonomous driving. Your work will span model architecture, data pipelines, evaluation frameworks and real-world deployment. You’ll work closely with AI Platform, Simulation, Robot Software and Model Release teams to build systems that are performant, adaptable and ready for production, while helping shape the long-term technical direction across Autonomy.

• Develop and improve end-to-end driving models, advancing their performance, robustness and generalisation.
• Lead technical initiatives in personalised and collaborative driving, including behaviour conditioning, comfort tuning and alignment with user preferences.
• Build evaluation pipelines and metrics to assess open-loop and closed-loop driving performance and product readiness.
• Curate and mine real-world and synthetic data to improve scenario diversity, coverage and feature-specific development.
• Collaborate across engineering teams to integrate models, accelerate iteration and support real-world deployment.
• Mentor senior engineers, drive technical alignment and influence architecture, training and deployment decisions.

• End-to-end driving intelligence:
  Advance the models that underpin assisted and autonomous driving, connecting model development with real-world performance.
• Personalisation, comfort and collaboration:
  Develop ML-driven behaviours that adapt to user preferences and support comfortable, collaborative driving.
• Evaluation and product readiness:
  Create frameworks that measure driving quality, robustness and feature performance in both open-loop and closed-loop settings.
• Data-driven model improvement:
  Use real-world and synthetic data to uncover gaps, broaden scenario coverage and support targeted feature development.
• Production-scale learning systems:
  Shape model architectures, training methodologies and deployment pathways, working across AI Platform, Simulation, Robot Software and Model Release.
• Technical leadership:
  Lead cross-team initiatives and help define the long-term technical direction of our autonomy capabilities.

• You have an extensive, proven track record of shipping deep learning systems to production.
• You bring deep expertise in deep learning, particularly sequential models, control, planning or perception.
• You’re proficient in Python, experienced with relevant languages such as C++ or CUDA, and confident using ML frameworks, especially PyTorch.
• You have a strong foundation in software engineering practices and experience building reliable, maintainable ML systems.
• You have worked with real-time systems or robotics, ideally including simulation-in-the-loop or vehicle-in-the-loop components.
• You can lead technical initiatives across teams, build alignment and mentor engineers.

• Experience in autonomous driving, imitation learning or trajectory prediction.
• Familiarity with personalisation, human behaviour modelling or driver intent inference.
• Experience integrating ML systems into production hardware or multi-agent simulation.

Not ticking every box?…