Driver Workload Estimation AI Engineer, Info Mobility Car
Woven City (Mobility BU)
Tokyo / Susono, Shizuoka
hybrid
About Woven by Toyota
Woven by Toyota is enabling Toyota’s once-in-a-century transformation into a mobility company. Inspired by a legacy of innovating for the benefit of others, our mission is to challenge the current state of mobility through human-centric innovation — expanding what “mobility” means and how it serves society.
Our work centers on four pillars: AD/ADAS, our autonomous driving and advanced driver assist technologies; Arene, our software development platform for software-defined vehicles; Woven City, a test course for mobility; and Cloud & AI, the digital infrastructure powering our collaborative foundation. Business-critical functions empower these teams to execute, and together, we’re working toward one bold goal: a world with zero accidents and enhanced well-being for all.
=========================================================================
TEAM
Toyota is redefining what it means to move. We're challenging the current state of mobility by enhancing the movement of people, goods, information and energy. Centered around three core concepts - A Living Laboratory™, Human-Centered, and Ever Evolving City™ - Woven City serves as a test course for mobility to fulfill our purpose of well-being for all.
We do this by bringing together a diverse community of people with a shared passion for the future of mobility to co-create, develop and refine innovative products and services. This cross-section of social infrastructure, mobility, and people provides a unique opportunity for inventors, residents and visitors to interact seamlessly with new technologies throughout daily life in an environment that emulates a real city.
The Info Mobility Car team in the Mobility BU develops driver support features that provide driving suggestions
and voice prompts to drivers.
We aim to enable safer and more comfortable driving experiences by leveraging in-cabin and external camera images and various vehicle sensor data, with driver “busyness” and state estimation algorithms as our core technology.
Working closely with software development teams and simulation-based evaluation teams, we continuously drive performance improvements of these features.
For more information about Woven City, please visit: https://www.woven-city.global/
WHO ARE WE LOOKING FOR?
We are looking for someone who can lead the development of ML-based algorithms that estimate driver
workload (busyness) by combining vehicle CAN signals, various in-vehicle sensors, and driver operation logs
as time-series data.
We welcome candidates who can leverage their expertise in driver state estimation, vehicle dynamics, sensor fusion, and machine learning to design and refine robust driver workload indices, while balancing them with other workload indicators such as surrounding-vehicle and vision-based measures.
We envision someone who is comfortable working in a high-uncertainty domain, iteratively testing hypotheses
with data, and collaborating with stakeholders to translate technical outcomes into product value.
workload (busyness) by combining vehicle CAN signals, various in-vehicle sensors, and driver operation logs
as time-series data.
We welcome candidates who can leverage their expertise in driver state estimation, vehicle dynamics, sensor fusion, and machine learning to design and refine robust driver workload indices, while balancing them with other workload indicators such as surrounding-vehicle and vision-based measures.
We envision someone who is comfortable working in a high-uncertainty domain, iteratively testing hypotheses
with data, and collaborating with stakeholders to translate technical outcomes into product value.
RESPONSIBILITIES
- Design, implement, and enhance ML-based driver workload (busyness) estimation algorithms that take vehicle CAN signals, various in-vehicle sensors, and driver operation logs as time-series inputs
- Build and operate training data infrastructure and evaluation pipelines, including label and annotation policy design, data preprocessing, and feature engineering
- Investigate and improve logics that combine CAN-based workload indicators with other workload measures, such as surrounding-vehicle information and image/vision-based indicators
- Design interfaces and specifications to feed workload estimation results into driving suggestion and voice prompt logic, and continuously improve overall feature performance
- Collaborate with software engineers, test engineers, UX members, and other stakeholders to align on requirements and evaluation metrics, and to organize and share experiment results and technical learnings
- Participate, as required by projects and business needs, in planning and conducting evaluations using simulators and on-road test vehicles (including business trips), and drive improvement cycles based on real-world findings
MINIMUM QUALIFICATIONS
- 3+ years of practical experience in software or algorithm development primarily using vehicle CAN signals, in-vehicle sensors, and driver operation logs as time-series data
- Practical experience developing algorithms using machine learning, deep learning, and/or statistical modeling
- Development experience in Python using major ML/DL frameworks (e.g., PyTorch, TensorFlow)
- Ability to independently drive the end-to-end ML development process from data preprocessing and feature design through training and evaluation
- Communication skills to work with multiple stakeholders and clearly explain technical topics and evaluation results
- Willingness to travel for business purposes as required by project or business needs
- Business level Japanese proficiency and conversational level English
NICE TO HAVES
- Ability and willingness to work at the Susono office
- Development or evaluation experience in domains such as in-vehicle systems, driver assistance (ADAS), driver monitoring, or robotics
- Experience in feature engineering and developing driver workload or driver state estimation algorithms using vehicle CAN signals, various in-vehicle sensors, and driver operation logs as time-series data
- Experience deploying ML models to production, including edge/embedded optimization, inference pipeline construction, and model operations
- Experience using simulators (e.g., Unity) for algorithm evaluation or data generation
- External outputs in ML, signal processing, or related fields, such as competition results or academic publications
- Bachelor’s degree in computer science, electrical/electronic engineering, control engineering, or a related field, or equivalent practical experience
=========================================================================
Important Points
・All interviews will be arranged via Google Meet, unless otherwise stated.
・The same job descriptions are available in both English and Japanese; therefore, we kindly ask that you apply to only one version.
・We kindly request that you submit your resume in English, if possible. However, Japanese resumes are also acceptable. Please note that, depending on the English proficiency requirements of the role, we may request an English version of your resume later in the process.
WHAT WE OFFER
・Competitive Salary - Based on experience
・Work Hours - Flexible working time
・Paid Holiday - 20 days per year (prorated)
・Sick Leave - 6 days per year (prorated)
・Holiday - Sat & Sun, Japanese National Holidays, and other days defined by our company
・Japanese Social Insurance - Health Insurance, Pension, Workers’ Comp, and Unemployment Insurance, Long-term care insurance
・Housing Allowance
・Retirement Benefits
・Rental Cars Support
・In-house Training Program (software study/language study)
Our Commitment
・We are an equal opportunity employer and value diversity.
・Any information we receive from you will be used only in the hiring and onboarding process. Please see our privacy notice for more details.