Machine Learning Engineer, Adas

Wayve Wayve · Robotics · Herzliya, Israel · AV Engineering

Machine Learning Engineer focused on ADAS (Advanced Driver-Assistance Systems) at Wayve, a company developing Embodied AI for autonomous driving. The role involves the full ML lifecycle from data creation and pipelines to training, evaluation, and iteration of computer vision and 3D perception models. Emphasis is on shipping applied ML systems with real-world driving performance improvements, working with both on-car and offline ML systems.

What you'd actually do

  1. You’ll train, debug, and improve computer vision and 3D perception models, and iterate based on clear evaluation signals.
  2. You’ll work across the full ML lifecycle (data → training → evaluation → iteration), partnering with the team to decide what to tackle next based on where the system is underperforming.
  3. A meaningful portion of the role involves building scalable data pipelines (including auto-labelling / pseudo-labelling) to accelerate model development.
  4. You’ll help deliver core ADAS perception capabilities such as detection, classification, and instance segmentation, with domain focus across lanes, objects, traffic signs, and traffic lights.
  5. You’ll contribute to offline pipelines like tracking + 3D reconstruction that let us back-propagate “known good” labels through time and generate large labelled datasets.

Skills

Required

  • Computer Vision
  • 3D Perception
  • Deep Learning
  • ML Lifecycle Management
  • Data Pipelines
  • Model Evaluation
  • Applied ML Engineering

Nice to have

  • LiDAR
  • multi-view geometry
  • tracking
  • 3D reconstruction
  • online models
  • offline models
  • auto-labelling
  • pseudo-labelling

What the JD emphasized

  • built and shipped CV-focused deep learning systems
  • strong applied ML engineering (not research-only)
  • experience with 3D perception concepts or pipelines
  • comfortable owning work end-to-end, including evaluation and dataset generation
  • working under real product constraints

Other signals

  • end-to-end ML lifecycle
  • shipping ML models
  • computer vision
  • 3D perception
  • data pipelines
  • evaluation