Staff Machine Learning Engineer (Emergency Trajectory Models)

• As a Staff Machine Learning Engineer in Wayve’s AV Core organization, you will lead the technical direction and delivery of a learned emergency trajectory model for low-frequency, high-consequence maneuvers such as evasive steering and emergency braking

• You will take the programme from problem definition through modelling, evaluation, integration, and evidence for deployment

• Emergency maneuvers are rare, high-consequence events that place unusual demands on data, modelling, and validation

• The hard problem is not simply to train another trajectory head: it is to define the operating envelope of a specialist model, what evidence shows that it improves outcomes without introducing new failure modes, and how it integrates with the general driving model and surrounding system

• You will lead that work across AV Core and with partners across simulation, evaluation, safety, and product engineering

• Set the technical strategy and roadmap for the emergency trajectory model, including its behavioral scope, operating envelope, system interfaces, and measurable acceptance criteria

• Design and train trajectory-generating policies using the methods best supported by evidence, including behaviour cloning, reinforcement learning, or other sequential decision-making approaches

• Build a data strategy for rare emergency cases, combining fleet data, targeted mining, simulation, augmentation, and reweighting while controlling coverage gaps and unintended behavior

• Create rigorous open-loop and closed-loop evaluations for collision avoidance, evasive steering, emergency braking, recovery, robustness, latency, and regressions in nominal driving

• Lead integration into the shared driving stack, align technical decisions across teams, and raise the bar through architecture reviews, mentoring, and clear communication of risks, trade-offs, and evidence

Benefits

• Private healthcare: Choose our optional health insurance for comprehensive coverage for you and your family.

• Paid time off: Paid vacation plus public holidays and additional leave programs, ensuring you have time to unwind.

• Mental health resources: Through Spill, you can access therapy and mental health support.

• Community and socials: Join clubs or attend team socials to connect over hobbies, sports, or just for fun.

• Competitive compensation: Our compensation package includes cash and equity, making you a true partner in our success.

• Learning and development: Budgets for books, courses, and company-wide training to support your continuous growth.- Deep expertise developing learned trajectory-generation or policy models for embodied systems, including architecture design, objective design, training, and empirical validation

• Strong machine learning engineering skills in Python and PyTorch, with experience building reproducible training and evaluation systems on large, heterogeneous datasets

• Hands-on experience with behaviour cloning, reinforcement learning, or related methods, including objective design, distribution shift, robustness, and closed-loop failure analysis

• A track record of staff-level technical leadership: setting direction for ambiguous machine learning programmes, aligning multiple teams, and carrying work from research through production deployment

• Exceptional technical judgement and communication: able to make safety-relevant trade-offs explicit, define the evidence needed for decisions, and lead without relying on formal authority

• We understand that everyone has a unique set of skills and experiences and that not everyone will meet all of the requirements listed above. If you’re passionate about self-driving cars and think you have what it takes to make a positive impact on the world, we encourage you to apply

• Experience applying learned models in autonomous driving or robotics, with strong understanding of motion planning, vehicle dynamics, control, or collision avoidance

• Experience with specialist, fallback, redundant, mixture-of-experts, or model-routing architectures and the interfaces used to select between them

• Experience mining, generating, or evaluating rare events using simulation and fleet or real-world data

• Experience deploying learned policies under real-time latency, reliability, and compute constraints; proficiency in C++, CUDA, or systems optimisation

• Experience with multimodal, transformer-based, diffusion-based, or other generative trajectory or policy models