System & Data Scientist

Wayve•Sunnyvale, CA

5d•Hybrid

About The Position

Founded in 2017, Wayve is the leading developer of Embodied AI technology. Our advanced AI software and foundation models enable vehicles to perceive, understand, and navigate any complex environment, enhancing the usability and safety of automated driving systems. Our vision is to create autonomy that propels the world forward. Our intelligent, mapless, and hardware-agnostic AI products are designed for automakers, accelerating the transition from assisted to automated driving. In our fast-paced environment big problems ignite us—we embrace uncertainty, leaning into complex challenges to unlock groundbreaking solutions. We aim high and stay humble in our pursuit of excellence, constantly learning and evolving as we pave the way for a smarter, safer future. At Wayve, your contributions matter. We value diversity, embrace new perspectives, and foster an inclusive work environment; we back each other to deliver impact. Make Wayve the experience that defines your career! The role As part of our mission to scale end-to-end embodied AI for autonomous driving, we are building a world-class Data Management team focused on unlocking high-quality, targeted data acquisition that drives model performance and predictability. We are looking for a highly analytical and systems-minded ODD & Behavioral Competency Analyst to lead the analysis of Operational Design Domains (ODDs), traffic patterns, and regulatory behaviors across our target markets. This role will be critical in defining what data is needed, where, and how much , in order to build models with high Mean Time Between Failures (MTBF) and generalization capabilities across varied geographies.

Requirements

7+ years experience in systems engineering, automotive data analysis, data science, or a related field.
Experience analyzing or defining ODDs in the context of AV/ADAS technologies is a strong plus.
Familiarity with traffic regulations and human driving behaviors across multiple geographies.
Proficiency in data analysis tools (e.g., Python, SQL, GIS, Jupyter accessing large pools of data from frameworks like DataBricks) and ability to visualize ODD and scenario coverage metrics.
Ability to work cross-functionally and translate domain analysis into technical and product requirements.
Experience working in an agile, fast-scaling environment with a strong execution mindset.

Nice To Haves

MS or PhD in Physics, Statistics or Mathematics with specialism in traffic system modeling, autonomous driving deployment, or urban mobility analysis.

Responsibilities

ODD Characterization: Analyze and define the operational design domain (ODD) for each target market or region, including geography, infrastructure, weather, road types, traffic density, and local driving behaviors. Identify ODD boundaries, edge conditions, and failure triggers to inform data collection and system design.
Behavioral Competency Mapping: Build and maintain a taxonomy of behavioral competencies (e.g., merging, yielding, unprotected turns, interacting with pedestrians) required to safely operate in each ODD. Quantify the complexity and frequency of each competency based on local traffic data, regulations, and real-world observations.
ODD Permutation & Scaling Framework: Develop a framework to compute and prioritize permutations of ODD parameters and behavioral competencies to optimize data collection, scenario coverage, and scaling efficiency. Recommend minimal data slices needed to support safe and predictable system performance in a new region.
Current model behavioural Pattern Analysis: Analyze current model kpi patterns, and common driving behaviors, assess differences in required system behavior and edge case risks. Collaborate with safety and product on findings and proposals for behavioural improvement.
Cross-functional Collaboration: Work closely with data engineering, safety, simulation, product, and deployment teams to turn ODD and competency insights into actionable data strategies and deployment plans. Provide input to scenario library development, synthetic data generation, and test case prioritization.
Predictability & MTBF Guidance: Use historical data and statistical models to identify data gaps or high-variance behaviors that impact MTBF performance. Provide guidance on what additional data is needed to reach MTBF targets in each ODD segment.