Lead Perception Engineer

Job description

**About Woven by Toyota** [Woven by Toyota](https://woven.toyota/en) 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 At Woven by Toyota, we work on some of the most challenging problems in autonomy from 3D geometric computer vision and perception to prediction, motion planning, and safe deployment of ML systems in real vehicles. Our AD/ADAS organization develops production‑grade autonomy and active safety technologies that operate in complex, uncertain real‑world environments and ship at global scale. You’ll collaborate daily with ML researchers, software engineers, robotics engineers, and hardware teams to design, build, and deploy perception and world‑understanding systems that directly influence how vehicles see, reason about, and interact with the world. ### WHO ARE WE LOOKING FOR? We are seeking a Lead Engineer to report to the Global Head of World Understanding to drive the multi-year roadmap, architecture, metrics, and technical strategy for software components contributing to understanding around the vehicle. A system thinker with technical depth in machine learning approaches to complex systems. This engineer will accelerate the adoption of data-driven and deep learning methodologies, focusing on ML system design and verification, supervised/unsupervised learning, multi-modality, multi-tasks training, and temporal/sequential modeling. This role emphasizes faster and more cost-efficient model iteration, data-driven validation strategies, and unlocking new safety/performance capabilities through advanced ML. The role also requires strong communication skills, an aptitude for mentoring tech leads, influencing and collaborating with diverse stakeholders, including TMC, in identifying deep technical challenges, developing solutions, and executing on the delivery of our autonomy mission. ### RESPONSIBILITIES - Driving the technical vision and multi-year strategy for World Understanding (including perception, mapping, fusion, on-board/off-board) software - Leading project execution, defining efficient engineering processes, and mitigating risks - Collaborate with cross-functional teams such as Data, Behavior (Planner/Controller/HMI), Developer Ecosystem, and Product Delivery while influencing technical decisions across the organization to drive innovation, ensure seamless system integration, and improve overall engineering efficiency - Develop state-of-the-art models to deliver desired driving environments in various sensor configurations - Increase speed of the component- and system-level model iteration while maintaining cost efficiency - Incorporate data-driven approaches to improve system performance and unlock new capabilities for safety - Maintain the functional architecture design and lead review of technical designs - Drive organizational metrics towards performance, safety, and quality - Maintain external presence of the department through papers, patents, and presentations - Assess and mitigate risk to the technical program - Act in partnership with other Lead Engineers in AD/ADAS to solve high impact cross-functional issues - Mentor and support engineers, fostering growth through code reviews, knowledge sharing, and collaboration with cross-functional teams to align technical solutions with business goals - Design reusable software components as part of an integrated system - Understand and fulfill the software practices that produce maintainable code, including simulation, continuous integration, code review, HIL testing, and in-vehicle testing - Build component and system level validation strategies that are leveraged to resolve complex interactions between components, increase performance, and evaluate design tradeoffs related to data-driven practices ### MINIMUM QUALIFICATIONS - 10+ years of professional experience with machine learning applications or applied science - MS or PHD in Machine Learning, Mechanical, Electrical, Computer, Aerospace Engineering, or similar - Deep expertise in ML algorithms, frameworks, data-driven methods, supervised/unsupervised learning, multi-modality, multi-tasks training, and temporal/sequential modeling, and deployment of ML models at scale - Strong R&D potential in algorithm design, data-driven approaches to safety, and large-scale, complex systems architecture, and requirements-driven development - Experience with utilizing deep learning frameworks to increase speed and ease of development - Experience with temporal data and/or sequential modeling - Experience with code quality and systems safety processes for production code delivery, with respect to data-driven methodologies and model validation - Strong, practical understanding of real-time system development, performance issues, testing modalities, and tradeoffs - Ability to write code in C++ and python - Ability to lead in globally distributed team - You are an excellent communicator, skilled collaborator, and principled colleague ### 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 computer vision ([e.g.multi-view](http://e.g.multi-view) geometry, camera calibration, depth estimation, neural radiance fields, gaussian splatting, simultaneous localization and mapping) - Experience with Planner ML system design (e.g. including supervised/unsupervised learning, reinforcement learning, diffusion policy) - Experience with robot motion planning (e.g., trajectory optimization, sampling-based planning, model predictive control) - Japanese language skills