Senior Machine Learning Engineer, Vehicle Perception

Team: AD/ADAS

Location: Palo Alto, CA

Commitment: Employee

Workplace Type: hybrid

TEAM

The Vehicle Perception team at Woven by Toyota tackles the core challenges of machine learning for 3D perception, sensor fusion, and computer vision in autonomous vehicles. Our work involves a variety of challenges, such as analyzing petabytes of multimodal driving data, solving optimization problems in computer vision, minimizing latency on hardware accelerators, deploying scalable and efficient machine learning (ML) training and evaluation pipelines, and designing novel neural network architectures to advance state-of-the-art ML for onboard perception. We are looking for doers and creative problem solvers to join us in improving mobility for everyone with human-centered automated driving solutions for personal and commercial applications.

WHO ARE WE LOOKING FOR?

The team is looking for a skilled Machine Learning Engineer to help advance a cutting-edge machine learning system for perception foundation models leveraging large-scale multimodal sensor data. You will have the chance to design and implement innovative machine learning models for our next-generation autonomous vehicle platform, influencing millions of Toyota production vehicles. We are looking for individuals who are passionate about self-driving car technology and its potential impact on humanity. Furthermore, we highly value candidates who exhibit a "giver" mindset, consistently seeking opportunities to assist their colleagues while maintaining a strong focus on delivering solutions to production.

RESPONSIBILITIES

• Senior Lead the design and development of perception foundation models for autonomous vehicles, unifying diverse sensor data for scalable 3D scene understanding.
• Deploy scalable and efficient ML models on our autonomous vehicle platform.
• Integrate modern technologies with rigorous safety standards while maintaining cost efficiency.
• Significantly contribute to development of needed components for end-to-end ML training and deployment, from data strategy to optimization and validation.
• Be a champion of the scientific method and critical thinking in inventing state-of-the-art deep learning solutions
• Work in a high-velocity environment and employ agile development practices.
• Collaborate closely with teams such as Perception, Motion Planning, Simulation, Infrastructure, and Tooling to drive unified solutions.
• Work in a hybrid workspace, with the requirement to be present in our Nihonbashi (Japan), Palo Alto (California), or Ann Arbor (Michigan) offices three days per week.

MINIMUM QUALIFICATIONS

MS or PhD in Machine Learning, Computer Vision, Robotics or related quantitative fields, or equivalent industry experience.

3+ years of experience with Python, any major deep learning framework (PyTorch preferred), and software engineering best practices

3+ years of experience with deep learning approaches such as supervised/unsupervised learning, transfer learning, multi-task learning, and/or deep reinforcement learning.

3+ years of experience covering machine learning workflows, data sampling and curation, pre-processing, model training, ablation studies, evaluation, deployment, and inference optimization.

Experience working with large-scale foundation models, including pretraining, multimodal architectures, self-supervised learning approaches.

Deep understanding of runtime complexity, distributed/cloud ML infrastructure, data pipeline architecture,resource-aware optimization.

Comfortable in writing C++ code to help integrate with our autonomous vehicle platform.

Strong leadership skills to influence others and the team's technical strategy.

Strong communication skills with the ability to communicate concepts clearly and precisely.

NICE TO HAVES

Published research at top-tier conferences (NeurIPs, CVPR and similar).

Proven track record of deploying ML models at scale in self-driving or related fields.

Experience with offboard, auto-labeling, or "data-engine" pipelines, including mining, curation, active learning, and ground-truth-free evaluation for large-scale datasets.

Hands-on experience with vision-language models (VLMs), world models, video prediction, or latent dynamics models for autonomous systems or robotics.

Experience leveraging foundation models across multiple platforms and sensor setups, including distilling larger models into efficient real-time variants.

Familiarity with production-level coding and deployment onto embedded platforms, optimizing for latency and hardware constraints.

Experience in self-driving challenges (Perception, Prediction, Mapping, Localization, Planning, Simulation).