Tech Lead, ML Engineer - Av Product Engineering

Wayve Wayve · Robotics · Sunnyvale, CA · AV Engineering

Tech Lead ML Engineer for AV Product Engineering, focusing on navigation workstream for L2+, L3, and robotaxi products. Owns the full lifecycle from model training to deployment in production vehicles. Requires strong ML engineering experience, Python/C++/CUDA proficiency, PyTorch, and experience with transformer/multimodal architectures.

What you'd actually do

  1. Lead the navigation workstream, including route planning, rerouting, and driving across L2+, L3, and robotaxi products.
  2. Train and deploy end-to-end models for navigation and driving features, owning the full lifecycle from model training through to vehicle integration and production deployment.
  3. Define the roadmap and technical vision for navigation ML within the AV Features team, helping shape the direction of L2+ driving features.
  4. Collaborate closely with the Evaluation, Robot Software, and Data Platform teams to iterate rapidly and improve model performance.
  5. Leverage closed-loop and open-loop evaluation frameworks to measure driving quality and validate production readiness.

Skills

Required

  • 7+ years of ML engineering experience
  • strong track record of shipping deep learning systems to production
  • Proficient in Python
  • Proficient in C++
  • Proficient in CUDA
  • ML frameworks (esp. PyTorch)
  • solid foundation in software engineering practices
  • Hands-on experience with transformer-based architectures
  • Hands-on experience with multimodal architectures
  • vision-language models (VLM)
  • vision-language-action models (VLA)
  • Demonstrated ability to train and deploy end-to-end ML models for production systems
  • Strong understanding of end-to-end learning approaches for driving
  • Strong understanding of embodied AI
  • Ability to take full ownership of a technical workstream

Nice to have

  • Prior work in autonomous driving
  • imitation learning
  • trajectory prediction
  • AV industry experience
  • perception team experience
  • planning team experience
  • controls team experience
  • evaluation team experience
  • Experience with closed-loop simulation
  • Experience with open-loop evaluation for autonomous driving or robotics systems
  • Familiarity with navigation problems
  • Familiarity with route planning
  • Familiarity with multi-modal sensor fusion
  • Research publications in relevant areas (machine learning, robotics, computer vision)

What the JD emphasized

  • shipping deep learning systems to production
  • end-to-end ML models for production systems
  • take full ownership of a technical workstream

Other signals

  • shipping deep learning systems to production
  • end-to-end models for navigation and driving features
  • vehicle integration and production deployment
  • technical direction for navigation ML