• Lead E2E model design and development — define architectures that directly map multi-modal sensor inputs (camera, LiDAR, radar, HD maps) to mid- or high-level driving actions or cost functions. • Drive large-scale training and evaluation for E2E learning, integrating data from perception, behavior prediction, and control systems. • Develop and refine learning objectives that align with real-world driving metrics: safety, comfort, compliance, and efficiency. • Architect scalable pipelines for multi-task, multi-modal learning, leveraging both real-world and synthetic data. • Prototype and evaluate new paradigms such as differentiable planning, imitation learning, reinforcement learning, and world models for AV behavior. • Collaborate cross-functionally with Perception, Prediction, and Motion Planning teams to align interfaces and ensure consistency between learned and modular components. • Establish robust evaluation frameworks for E2E performance, including closed-loop simulation and on-road validation. • Mentor engineers and scientists in large-scale experimentation, model interpretability, and data-driven debugging. • Stay at the frontier of ML research, exploring advancements in foundation models, sequence modeling, self-supervision, and generative world representations.