Level 5, part of Woven Planet, is developing self-driving technology using a machine-learned approach to create safe mobility for everyone. Our goal is to build level 4 autonomous vehicles to improve personal transportation on a global scale. Woven Planet is a software-first subsidiary of Toyota whose vision is to create mobility of people, goods, and information that everyone can enjoy and trust.
As part of Woven Planet, Level 5 has the backing of one of the world’s largest automakers, the talent to deliver on our goal, and the opportunity for near-term product impact and revenue—a combination rarely seen in the AV industry.
Level 5 is looking for doers and creative problem solvers to join us in improving mobility for everyone with self-driving technology. We’ve built a diverse and talented group of software and hardware engineers, and each has the opportunity to make a meaningful impact on our self-driving stack.
Our team of more than 300 works in brand new garages and labs in Palo Alto, tests AVs at our dedicated test track in the Silicon Valley, and explores the AV industry’s most compelling research problems at our office in London. With support from more than 800 Woven Planet colleagues in Tokyo, Level 5’s work to improve the future of mobility spans the globe. And we’re moving fast — in Level 5’s first 18 months, we launched an employee pilot, and are now testing our fourth generation vehicle platform in San Francisco. Learn more at level-5.global.
You will be interacting on a daily basis with software engineers, machine learning specialists, and researchers to tackle some of the most challenging problems in AI and robotics. We work on a diverse set of problems ranging from solving motion planning problems in challenging traffic situations, to minimizing latency on hardware accelerators, to designing novel neural network architectures.
The team is looking for a deep learning expert to drive the research and deployment of the next generation of deep learning models for Autonomous driving. As an expert in machine learning, you will be working with the Motion Planning Team on developing a machine learning first approach to motion planning that combines the latest findings in deep learning, reinforcement learning, imitation learning, motion planning, and robotics. The ideal candidate will have published some deep learning research in top-tier conferences such as NeurIPs or CVPR, built and deployed real-world deep learning products, and worked in a fast-paced environment along with other highly talented engineers. We recognize the unique capabilities each team member can bring, though and encourage applicants to reach out even if they do not match all of the characteristics described below.
- Work in a small, high-velocity team of engineers and researchers
- Develop state-of-the-art methods that leverage imitation learning, deep reinforcement learning, and large-scale data to develop a machine learning first approach to motion planning, taking into account many factors such as scalability, inference speed, and generalization power.
- Train neural networks on massive volumes of data, and build the necessary metrics and introspection tools to enable rapid iteration
- Be a champion of the scientific method and critical thinking in inventing state-of-the-art deep learning solutions but is also a leader in applying rigorous engineering practices during validation and deployment
- Stay up to date with the latest research and trends in the fields and apply new state-of-the-art solutions.
- Collaborate closely with teams such as Perception, Simulation, Infrastructure, Tooling to drive unified solutions
- Advance the state-of-the-art and represent Level 5 at top-tier conferences (e.g. CVPR, NeurIPs, ICCV, CoRL, ICRA)
- Advanced degree (Ph.D. preferred) in Machine Learning, Robotics, CS (or other related fields), or other quantitative fields or relevant work experience.
- Minimum 3 years experience preferred
- Experience with learning-based planning approaches like imitation learning, reinforcement learning and state-of-the-art techniques for sequential modelling like Transformer architectures, and state-of-the-art vector/point-based input representations.
- Programming experience implementing cutting-edge deep learned ML solutions using PyTorch / Tensorflow and distributed training.
- Understanding of ML workflow: preparing and sampling the data, implementing and training ML models, evaluating results, running ablation studies, deploying inference on different platforms
- (Nice to Have) Experience with robot motion planning techniques like trajectory optimization, sampling-based planning, model predictive control, etc or self-driving problems (Perception, Prediction, Mapping, Localization, Planning, Simulation)
- (Nice to Have) Experience with temporal/sequential modeling and/or reinforcement learning.
- (Nice to Have) Experience targeting power-efficient, edge-compute architectures
・We are an equal opportunity employer and value diversity.
・We pledge that any information we receive from candidates will be used ONLY for the purpose of hiring assessment.