Lead Perception Engineer
Woven by Toyota2 months ago
Tokyo, JapanStaff+
Responsibilities
- Drive the technical vision, roadmap, architecture, metrics, and strategy for world-understanding software including perception, mapping, and fusion.
- Lead project execution, technical design reviews, engineering processes, risk mitigation, and cross-functional technical decisions.
- Develop and deploy machine learning models for varied sensor configurations, including supervised and unsupervised learning, multimodal and multitask training, and temporal or sequential modeling.
- Improve component- and system-level model iteration speed, cost efficiency, safety, performance, and validation.
- Design reusable software components and maintain functional, system-level, and data-driven validation strategies.
- Ensure maintainable production software practices including simulation, continuous integration, code review, HIL testing, and in-vehicle testing.
- Mentor engineers and technical leads while collaborating with ML researchers, software, robotics, hardware, data, planning, and product teams.
- Represent the department through research papers, patents, presentations, and other external engagement.
Requirements
- 10+ years of professional experience with machine learning applications or applied science.
- MS or PhD in Machine Learning, Mechanical Engineering, Electrical Engineering, Computer Engineering, Aerospace Engineering, or a similar field.
- Deep expertise in ML algorithms, deep learning frameworks, data-driven methods, supervised and unsupervised learning, multimodality, multitask training, temporal or sequential modeling, and large-scale ML deployment.
- Experience with model development, temporal or sequential data, production code quality, systems safety processes, model validation, and real-time system performance tradeoffs.
- Ability to write production code in C++ and Python and lead globally distributed teams.
- Strong R&D capability in algorithm design, data-driven safety, complex systems architecture, and requirements-driven development.
- Preferred experience includes top-tier research publications such as NeurIPS or CVPR, self-driving ML deployment, computer vision, multi-view geometry, camera calibration, depth estimation, neural radiance fields, Gaussian splatting, SLAM, planner ML, reinforcement learning, diffusion policy, and robot motion planning.
- Japanese language skills are a nice-to-have.
Benefits
- Competitive salary based on experience.
- Flexible working time.
- 20 days of paid holiday per year and 6 days of sick leave per year, prorated.
- Saturdays, Sundays, Japanese national holidays, and other company-defined holidays off.
- Japanese social insurance including health insurance, pension, workers’ compensation, unemployment insurance, and long-term care insurance.
- Housing allowance, retirement benefits, rental car support, and in-house software and language training.
- Interviews are conducted via Google Meet unless otherwise stated, and applicants may submit an English or Japanese resume.
Categories
ML EngineeringRobotics
About Woven by Toyota
Woven by Toyota exists to accelerate Toyota’s once-in-a-century transformation from a car company into a mobility company. Rooted in a legacy of reinvention, we carry forward a singular founding principle: to innovate for the benefit of others. Today, we are driving this transformation from two vantage points: redefining how vehicles are built, experienced, and connected to the world to realize a true software-defined vehicle, and reimagining how people, goods, information, and energy move and interact in society to empower individuals from all walks of life. Through these two lenses, we combine bold innovation with real-world execution, bridging the gap between present and future to help Toyota evolve its business and its role in society.