Senior ML Platform Engineer - AD/ADAS

TEAM

At Woven by Toyota, we tackle Autonomy challenges at the intersection of AI, Robotics, and Advanced Driving. Our work involves a variety of challenges, such as analyzing petabytes of multimodal driving data, solving optimization problems, 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 Perception, Prediction, and Motion Planning. 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 Software Engineer or Machine Learning Engineer to join the Machine Learning Platform team, and work in close collaboration with and/or embedded in our ML teams to accelerate and scale up our overall ML engineering activities, enabling shipping Perception, Prediction and Planning ML models and our AD/ADAS stack to millions of Toyota customer vehicles.
We are looking for individuals who are passionate about self-driving car technology and its potential impact on humanity, and able to leverage cutting-edge technologies to solve real-world problems while also considering ML engineers’ productivity and cost efficiency. We are looking for individuals who exhibit a "giver" mindset, consistently seeking opportunities to assist their colleagues while maintaining a strong focus on delivering solutions to production.

RESPONSIBILITIES

Design, build, maintain, optimize and support the ML Platform’s systems and tools for perception, prediction, and planner development, allowing numerous ML engineers to effectively & efficiently iterate on dataset curation, ML modeling, training, evaluation and deployment of ML models into our functionally safe AD/ADAS stack, shipped in millions of Toyota vehicles.

Develop user-friendly tooling, frameworks and libraries to support the overall ML engineering effort, from ML modeling, to tracking performance metrics and introspecting failure modes.

Build and maintain efficient dataset generation, cloud training and evaluation pipelines.

Develop and review code with other ML and ML Platform engineers to facilitate rapid incremental improvements.

Optimize the current processes, tooling and supporting infrastructure to accelerate the overall ML engineering effort, and contribute to the long term strategy for several of our systems and products.

Work in a high-velocity environment and employ agile development practices.

Work in a hybrid workspace, with the requirement to be present in our Palo Alto (USA) office three days per week.

MINIMUM QUALIFICATIONS

BSc / BEng (MS / PhD nice-to-have) in Machine Learning, Computer Science, Robotics or related quantitative fields, or equivalent industry experience.

5+ years of experience with data structures, algorithms, design patterns, and software engineering best practices.

2+ years of experience with UNIX-based systems (Linux or similar), Python, and PyTorch/Tensorflow.

2+ years of experience in the full MLOps cycle covering data cleansing, data sampling, data curation, pre-processing, efficient data loading, distributed training, testing, evaluation, deployment, inference optimization and deployment in the cloud and on edge compute platforms.

Experience with Docker and CI systems such as GitHub Actions.

Business-level proficiency in English, able to write technical documents (e.g., for software documentation).

NICE TO HAVES

2+ years of experience with Apache Spark, Airflow, Flyte, Flink, Ray, or similar ML pipelines technologies.

2+ years using modern systems programming languages (e.g., Rust and/or C++) and a modern build system (preferably Bazel), and systems-level debugging knowledge, in a professional environment.

Experience with SIMD/SIMT parallelism, GPU programming, multithreading.

Experience with Terraform, AWS, Observability, and Kubernetes in production.

Experience with Google Big Query, Snowflake or AWS Redshift in production.

Experience in optimizing deep-learning models towards specific hardware targets.

Experience in self-driving, robotics, computer vision, or motion planning.

Experience working in a fast-paced environment, collaborating across teams and disciplines.

Business-level proficiency in Japanese.