Staff Machine Learning Engineer, Simulation

Wing•Palo Alto, CA

24d•Hybrid

About The Position

Wing is looking for a Staff Machine Learning Engineer, Simulation to join our Simulation team. This role is hybrid based in Palo Alto. Simulation is a core technology for Wing. We provide essential tools for R&D and are critical to ensuring the reliability of our fleet of autonomous aircraft. The simulation team’s work spans vehicle physics and sensor modeling, large-scale simulation frameworks, test infrastructure for backend verification and integrated avionics and system testing. The Staff Machine Learning Engineer, Simulation is a foundational role for someone who thrives on both technical execution and strategic growth. You will be a key driver in integrating advanced ML techniques into Wing’s simulation stack. You will define and execute the strategy for enhancing simulator realism, and develop industry-leading simulation solutions using advanced generative and reconstructive ML algorithms to model the real world.

Requirements

12+ years of experience developing and designing machine learning applications, autonomous systems, or simulation platforms.
B.S, M.S., or Ph.D. degree or equivalent practical experience in Computer Science, Machine Learning, Robotics, or a related field.
Demonstrated ability to lead technical ML projects of significant scope and complexity, driving initiatives from research to production-ready solutions.
Deep expertise in 3D World Modeling or 3D computer vision.
Familiarity with 3D reconstruction and rendering techniques (e.g., 3D Gaussian Splatting).
In-depth knowledge of generative AI, predictive world models, autoregressive models, or self-supervised learning from multi-modal sensor streams.
Hands-on experience with sim-to-real transfer, domain adaptation, and world models.
Experience developing testing frameworks and evaluating ML models for edge cases and rare events in complex systems.

Responsibilities

Lead the design, development and deployment of world models and generative systems for realistic and controllable sensor generation for large-scale simulation at Wing’s autonomous system.
Develop generative pipelines to build high-fidelity synthetic datasets, leveraging SOTA multimodal models, diffusion techniques and world-models to simulate complex 4D environments.
Partner with research teams across Alphabet to integrate advanced modeling techniques.
Champion sim-to-real efforts, using domain adaptation and transfer learning techniques to ensure our simulated models faithfully capture the behaviors of physical, on-vehicle systems.
Apply VLMs to enhance the understanding and controllability of our world simulation products.
Play a pivotal role in shaping the broader AI infrastructure across the organization, establishing best practices, optimizing workflow management for large-scale training, and championing foundational AI initiatives.