Senior Data Scientist

Wayve•Sunnyvale, CA
•Hybrid

About The Position

Wayve ships a new driving model baseline every week. The Model Integration & Release team runs simulation and on-road testing to decide whether candidates are ready to promote — and there is a significant opportunity to get more from the data we already collect. As our release process matures, the next step is building a deeper analytical layer: strengthening how we measure performance, turning on-road findings into better simulation tests, and aligning what we measure with what operators experience in the vehicle. This is a senior, high-impact role on the Model Integration & Release team. You'll own that analytical layer — turning evaluation outputs into findings that improve both our models and how we measure them. You'll work across simulation, on-road experiment data, and our internal evaluation tooling, partnering with Validation, Data Science, and Product. You'll have the autonomy and scope to improve how we evaluate — from identifying gaps in our measurement approach through to implementing changes that make our release decisions more confident and our feedback loops faster.

Requirements

  • Strong analytical and investigative skills — you’re comfortable going from a vague “something looks off” to a clear, evidence-backed conclusion
  • Hands-on experience working with ML evaluation data, driving performance metrics, or complex test results at scale, including statistical methods for A/B testing and experimentation (e.g., confidence intervals, distributions, and sampling)
  • Proficiency in Python or SQL; comfortable querying and analysing large datasets
  • Ability to operate with autonomy in a fast-moving environment — you can set your own priorities within a broader goal, and know when to fix something yourself vs. when to escalate or partner
  • Clear written communication — you turn messy investigations into concise, actionable recommendations for technical and non-technical audiences
  • Genuine curiosity about why a model behaves the way it does, and whether we’re measuring the right things

Nice To Haves

  • Experience in autonomous driving, robotics, or safety-critical ML systems
  • Familiarity with simulation-based testing, on-road experiment analysis, or statistical methods for comparing model behaviour
  • Experience working across product, safety, and engineering teams to define what “good” looks like
  • Exposure to OEM or partner validation workflows
  • Experience improving evaluation infrastructure or measurement methodology

Responsibilities

  • Shape how we learn from evaluation data — define what “going deeper” means in practice, and build the habits, tooling, and workflows that make it part of how we release models
  • Improve how we measure driving performance — identify blind spots, inconsistencies, and gaps in our simulation and offline metrics; drive improvements to our evaluation methods, suites, and scoring logic
  • Close the loop between on-road testing and offline evaluation — investigate what happens on-vehicle during release testing, determine whether our offline tests should have caught it, and turn those findings into concrete improvements to coverage and measurement
  • Perform day-to-day experiment analysis and apply statistical rigor to evaluation data to provide confident, data-driven promotion recommendations for new driving models
  • Expand what “good” means beyond intervention rates — develop and apply a richer view of model quality using the behavioural and operational signals we already collect
  • Partner with Data Science and Validation on how we define, implement, and maintain evaluation methods and ground truth
  • Support partner-facing quality investigations — help quantify and track issues raised through OEM QA workflows so they can be addressed within our release process
  • Turn investigations into durable improvements — document findings and recommendations in a way the team can act on within a weekly release cadence, and follow through so the same class of issue doesn’t recur

Benefits

  • Hybrid working policy that combines time together in our offices and workshops to fuel innovation, culture, relationships and learning, and time spent working from home.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service