Senior Staff Machine Learning Engineer, Perception, Simulation Realism
About The Position
Waymo is hiring a Senior Staff Machine Learning Engineer to lead the perception architecture for Sim GroundTruth. The role combines perception ML research, foundation models, and large-scale offline data engineering. The engineer will serve as the technical authority for perception models and guide and mentor ML engineers building high-fidelity 3D perception and petabyte-scale ML inference. The team builds a platform-agnostic Ground Truth engine for autonomous vehicle simulation and evaluation. It reprocesses onboard logs offline using ML foundation models to produce semantic signals that outperform real-time onboard software. The role will help scale this system as the backbone of large-scale evaluation, enabling rigorous and realistic software testing.
Requirements
- Master’s or PhD in Computer Science, Machine Learning, Robotics, or a related field; a PhD is preferred.
- Proven senior technical leadership setting technical vision, architecting complex ML systems, and mentoring senior engineers and research scientists.
- Demonstrated ability to gather requirements from diverse customers, align them into a unified technical roadmap, and negotiate roles and responsibilities across competing priorities.
- Hands-on technical leadership, including deep knowledge of codebases, evaluation and data pipelines, and model architectures.
- Deep understanding of Foundation Models (VLMs or MMLMs) and computer vision or perception architectures, such as Transformers, 3D detection, or scene reconstruction, particularly in post-training, fine-tuning, or inference-time scaling.
- Expert-level proficiency in Python, NumPy, and deep learning frameworks such as PyTorch or JAX.
Nice To Haves
- Experience building and scaling distributed systems or data pipelines at petabyte scale.
- Deep expertise in 2D and 3D object detection, multimodal sensor fusion (camera and LiDAR), tracking, and offboard ground-truth generation for autonomous vehicles.
- Proficiency in C++ and experience with production-grade ML deployment.
- Strong publication record at top-tier conferences such as CVPR, ICRA, or NeurIPS, or leadership in major open-source projects.
Responsibilities
- Architect a modular, extensible ML framework that can accommodate expanding signal requirements and scale unified Foundation Model architectures to hundreds of semantic categories while maintaining signal quality.
- Define the multi-year roadmap for signal quality, coverage, and reliability, and ensure signals set a high benchmark for ground-truth accuracy.
- Optimize high-fidelity perception model inference and compute efficiency across petabyte-scale datasets in collaboration with backend infrastructure leads.
- Serve as the primary interface for application owners, translating simulation needs into technical requirements and expanding adoption so major software launches are validated by the system.
- Provide technical leadership and mentorship to ML perception engineers, promote modeling best practices and architectural rigor, and drive execution on mission-critical perception initiatives.
Benefits
- Discretionary annual bonus program
- Equity incentive plan
- Company benefits program
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
