Machine Learning Engineer, AV Engineering
Wayve · Herzliya, Tel-Aviv District, Israel
About the role
Develop AI driver model architectures and training algorithms to enhance safety behaviors for L2 to L4 autonomous driving. Manage the full ML lifecycle from data curation and training to on-road validation and deployment.
What they look for
Requirements
Requires proven experience in training deep learning models and deploying them into production under real-world safety constraints. Experience with reinforcement learning, transformer networks, and PyTorch Lightning is highly desirable.
Full description
The role
We are hiring Senior and Staff ML Engineers that sit within Safety Systems / autonomy organisations, building critical behaviours for Level 2 to level 4 driving. It is highly product-focused: you will train and iterate on end-to-end driving models and get them shipped into the car on a fast timeline measured in months. The opportunity is to own the full loop from data and training through evaluation and on-road validation, with direct impact on high-priority commercial deliveries (including the Nissan MVP). You will join a small, high-ownership teams at the point of rapid growth, where execution and real-world outcomes matter.
Key responsibilities
- Develop the AI driver model architecture and training algorithms to introduce and enhance the safety behaviors for L2/L3/L4
- Own key parts of the training model lifecycle, including evaluation strategy, success metrics, and iteration planning.
- Mine, bucket, and curate real-world and synthetic data to teach specific driving behaviours, and implement data schemes to support training.
- Run and analyse on-road and offline experiments, translate results into clear next steps, and drive improvements through repeated training cycles.
About you
In order to set you up for success as a Machine Learning Engineer at Wayve, we’re looking for the following skills and experience.
Essential
- Proven experience training deep learning models, with clear end-to-end ownership (data, training, evaluation, iteration).
- Proven Experience taking ML models into production, including working through real-world constraints and quality and safety requirements.
Desirable
- Reinforcement learning experience (especially where it materially improved real-world performance).
- Experience with end-to-end driving models and / or transformer networks
- Automotive or OEM experience, or prior work that involved deploying ML into safety-critical systems.
- Experience with a Pytorch lightning training infrastructure
This is a full-time role based in our office in Israel. At Wayve we want the best of all worlds so we operate a hybrid working policy that combines time together in our offices and workshops to fuel innovation, culture, relationships and learning, and time spent working from home.