SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Wayve is building an AI platform for autonomous driving using an end-to-end learning approach. The Vehicle Generalization team makes it efficient and scalable to deploy Wayve's autonomy stack across diverse vehicle platforms by improving how AI models generalize to changes in perception (cameras, intrinsics, field of view, lens distortion, calibration) and embodiment (vehicle dynamics, actuation limits, rig geometry).
In this role, you'll be a hands-on machine learning engineer working on the technical foundations that enable zero-shot transfer across vehicle platforms. Your day-to-day will include:
- Designing and training models robust to vehicle differences using conditioning, augmentation, and other techniques for vehicle kinematics and camera parameters
- Creating benchmarks and metrics for cross-platform performance, translating results into actionable decisions for model and platform teams
- Root-causing on-road issues (late turns, lane-keeping, steering problems) by working with controls, calibration, and OEM engineers to isolate model problems from system problems
- Moving research into production in collaboration with Driving Core and application engineering teams
- Supporting customer programmes, including some travel
- Mentoring teammates and raising the bar for ML engineering across the team
You'll work on pre- and post-training methods for zero-shot transfer, robustness to camera configuration and vehicle dynamics changes, the Generalization Benchmark, real-world multi-sensor driving data, and production deployment with major OEM partners.
Wayve operates a hybrid model combining in-person collaboration with remote work. The role is based in Sunnyvale, CA (preferred) or London, with some travel required for customer support.
REQUIREMENTS:
- Several years of experience building and shipping ML systems in PyTorch and Python, including training at scale, debugging experiments, and rigorous evaluation
- Strong robotics or automotive background in state estimation, sensor fusion, calibration, vehicle dynamics, or controls
- Systems perspective to trace problems through sensors, data, models, and actuation
- Experience working with real-world, multi-sensor driving or robot data
- Clear communication across teams and comfort owning ambiguous problems from start to finish
NICE TO HAVE:
- Experience with end-to-end or learned driving and planning policies, imitation learning, or reinforcement learning
- Platform bring-up or deployment experience across multiple vehicles
- C++ skills and on-vehicle or embedded deployment experience
