As the Director for Simulation and Evaluation, you will sit at the center of the Global AI Backbone, architecting the multi-level simulation ecosystems required to train, evaluate and validate next-generation Foundation Models. You will bridge the gap between high-fidelity sensor simulation and generative world models, ensuring our AI systems are statistically proven to be safe and robust before hitting the road.
This is a global role that requires you to define and manage a global simulation and evaluation ecosystem that enables continuous development and deployment of our ADAS systems.
Key Responsibilities:
- Lead AI Simulation & Foundation Model Strategy: Define the roadmap for high throughput, closed-loop simulation.
- Research and propose new methodologies to assess the quality, safety, and realism of ML models used for training, evaluation and validation of L2++ and L4 automated driving stacks.
- Architect Evaluation Frameworks: Build the infrastructure. Develop tools that allow for rapid iteration of Foundation Models, ensuring model improvements translate into measurable gains in fleet-wide performance.
- Drive Generative AI Innovation: Lead the development of World Models to predict and generate complex, realisticedge cases. Build data pipelines for signal discovery, data labeling, and metric computation based on large-scale simulations.
- Production Release Authority: Establish the "gold standard" for evaluation that informs SoP (Start of Production) and model release decisions. Translate complex simulation data into technical strategy documentation for executive decision-making.
- Global Technical Leadership: Lead, mentor and inspire a cross-functional global team of SWEs, Data Scientists, and ML experts, fostering a culture of rigorous statistical validation and innovative engineering.