Hybrid ML Engineer for Autonomous Driving & Personalization

Icehouseventures; Germany (OH); Hybrid; USD 102,412 - 170,688; Full time

Job summary

Wayve in Leonberg is seeking a Machine Learning Engineer to push model-based autonomous driving, focusing on core driving performance and features like personalization and collaboration.

You will design ML-driven behaviors, work on model architectures, data pipelines, evaluation, and production deployment, collaborating with AI Platform, Simulation, and Model Release teams in a hybrid office-based role.

Qualifications

• Proven track record of shipping DL systems to production.
• Expert in deep learning (sequential models, control, planning, or perception).
• Proficient in Python and other relevant languages (C++ and CUDA) and ML frameworks (PyTorch).
• Experience with real-time systems or robotics, ideally with simulation- or vehicle-in-the-loop components.
• Ability to lead technical initiatives across teams, mentor engineers.

Responsibilities

• Develop and improve end-to-end driving models with state-of-the-art performance and robustness.
• Lead projects on personalized and collaborative driving, including behavior conditioning and comfort tuning.
• Build evaluation pipelines and metrics for closed-loop and open-loop driving performance.
• Curate and mine real-world and synthetic data to drive scenario diversity.
• Influence architecture choices, training methodologies, and deployment pathways for production-scale systems.
• Collaborate across teams to ensure integration and fast iteration.
• Mentor senior engineers and shape long-term technical direction.

Skills

Shipping deep learning systems

Deep learning

Python

C++

CUDA

PyTorch

Software engineering

Real-time systems

Leadership

Tools

PyTorch

CUDA

Job description

Wayve in Leonberg is seeking a Machine Learning Engineer to push model-based autonomous driving, focusing on core driving performance and features like personalization and collaboration.

You will design ML-driven behaviors, work on model architectures, data pipelines, evaluation, and production deployment, collaborating with AI Platform, Simulation, and Model Release teams in a hybrid office-based role.