Staff Engineer, Machine Learning

We are CARIAD, an automotive software development team with the Volkswagen Group. Our mission is to make the automotive experience safer, more sustainable, more comfortable, more digital, and more fun. To achieve that we are building the leading tech stack for the automotive industry and creating a unified software platform for over 10 million new vehicles per year. We’re looking for talented, digital minds like you to help us create code that moves the world. Together with you, we’ll build outstanding digital experiences and products for all Volkswagen Group brands that will transform mobility. Join us as we shape the future of the car and everyone around it.

Role Summary:

The Staff Engineer, Machine Learning, is responsible for leading the development of a single-stage, end-to-end driving model for our Level 2++ to Level 4 Automated Driving stacks. This role leads design, implementation and validation of reinforcement learning-based models using a world-model simulation environment and leverages multi-modal sensor inputs such as camera and radar data to generate driving trajectories.

This role focuses on bridging advances in multi-modal foundation models with the practical challenges of real-time, safety critical embedded deployment. The Staff Engineer, Machine Learning ensures the model is robust, generalizes well, and meets safety standards across a wide range of driving scenarios. This role works closely with embedded engineers, data engineers, and MLOps/DevOps engineers, to create a scalable, high-performance system that delivers real-world impact.

Role Responsibilities:

Model Architecture & Training Strategy

• Research, evaluate, and decide single-stage, end-to-end ADAS model approaches and architectures
• Design and train state-of-the-art end-to-end machine learning models for the ADAS stack
• Define and evolve single-stage training strategies for end-to-end models in collaboration with data engineering and MLOps teams

Reinforcement Learning & Multimodal Modeling

• Oversee the build-up and optimization of a simulation-based reinforcement learning framework
• Train models using reinforcement learning approaches within simulation or world-model environments and reinforcement learning frameworks
• Work with real and synthetic multi-modal sensor data (camera, radar, lidar) to design models that effectively leverage all available data modalities
• Ensure models generalize across diverse driving scenarios and operational conditions

Evaluation, Deployment & Optimization

• Evaluate and benchmark models against real-world driving use cases using scalable evaluation pipelines
• Collaborate with embedded engineering teams to support model optimization, deployment on embedded hardware, and system integration
• Support model integration, performance tuning, and issue resolution during deployment and validation phase

Technical Collaboration & Continuous Improvement

• Partner with embedded, data, and platform teams to align model development with system constraints and deployment requirements
• Share technical insights and lessons learned to improve overall ADAS machine learning development practices

General Skills:

• Deep knowledge in End2End-AI models for automated driving functionalities
• Strong software engineering skills, including the ability to write clean, maintainable, and testable production-quality code
• Strong analytical and debugging skills, with the ability to evaluate tradeoffs and select appropriate technical solutions
• Ability to independently work on moderately complex technical problems, exercising sound judgment in ambiguous problem spaces
• Strong written and verbal communication skills, with the ability to clearly explain complex technical concepts to diverse audiences
• Ability to collaborate effectively with multiple teams, including working across geographies and time zones

Required Specialized Skills:

• Deep Learning expertise on foundation models and VLAMs for Automated driving with a background in CNNs, transformers and spatio-temporal models
• Hands on experience with machine learning frameworks such as PyTorch (or equivalent)
• Reinforcement learning experience, including training agents in simulation environments