**About the Role** We are looking for a Senior Applied Scientist with a passion for building software solutions where customer experiences take centre stage, and products are built with service quality at heart. We are building a real-time data platform to enable customer experience observability and analytics at scale: key ingredients to ensure we deliver best-in-class experiences for our users. The platform helps detect and respond to degradations in customer experience, supports safe and fast feature rollouts through real-time monitoring, and powers deeper analytics that inform product improvements, enabling both reactive and proactive service quality processes. This is an outstanding opportunity for an applied ML scientist with a collaborative spirit to the core, who will work with engineering, product, design, and peer data scientists to drive an ambitious observability platform. It’s a high-impact role where you will collaborate on challenges across domains and functions, spanning time-series anomaly detection, statistical monitoring and guardrails, and the data/metrics foundations needed to make customer experience measurable and actionable. You enjoy building solutions that take into account both the customer experience on one side (spenders and earners as the subject of study) and the tooling experience on the other (developers, product managers, and data scientists as users). If you have the technical chops, we invite you to join us to solve tough large-scale data challenges, develop data insights, and raise the bar of service quality. **What You Will Do** **Incident Detection & Mitigation** - Design and improve state-of-the-art anomaly detection and alerting for multivariate time series and derived experience metrics. - Build methods to reduce alert fatigue (deduplication, grouping, correlation, prioritization) and improve time-to-detection and time-to-resolution. - Contribute to intelligent incident response workflows: triage signals, suspected root-cause hints, and mitigation recommendations (in partnership with engineering/oncall stakeholders). **Rollout Safety & Speed (Experimentation & Monitoring)** - Develop statistical monitoring approaches for real-time rollout safety (e.g., sequential monitoring / near-real-time A/B style guardrails). - Help define and validate reliable metrics and thresholds that catch regressions early while minimizing false alarms. - Support fast iteration: establish evaluation frameworks, backtesting, and simulation to understand tradeoffs. **Analytics & Data Infrastructure Enablement** - Partner on analytics/metrics infrastructure that makes data “observability-ready”: consistent definitions, clean pipelines, and scalable feature/metric computation. - Advise on instrumentation gaps and data quality issues that limit detection, diagnosis, or analytics usefulness. - Help teams onboard new user flows and metrics into monitoring/analytics in a repeatable, low-friction way. **Scientific & Operational Excellence** - Define success metrics for detection systems (precision/recall, latency, stability, coverage) and create evaluation harnesses using historical incidents and annotated alerts. - Communicate results clearly to technical and non-technical stakeholders; drive alignment on tradeoffs and roadmap. **Basic Qualifications** 1. M.S. or Ph.D. in Computer Science, Machine Learning, Statistics, Operations Research, or other quantitative fields. 2. 6+ years of proven experience as an Applied Scientist, Machine Learning Scientist, Machine Learning Engineer, Research Scientist or equivalent. 3. **Strong expertise in anomaly detection**, with experience building production-grade, scalable detection and alerting pipelines for large-scale, real-time systems. 4. Excellent communications skills in a cross-functional setting. 5. Thought leadership to drive multi-functional projects from conceptualisation to productionization. 6. Experience in production coding and deploying ML, statistical, optimization models in real-time systems. 7. Ability to use Python or other programming languages to work efficiently at scale with large data sets in production systems. 8. Proficiency in SQL, PySpark, and experience with any of the following: Spark, Hive, Kafka, Pinot. **Preferred Qualifications** 1. Experience with real-time or near-real-time pipelines and large-scale data systems (e.g., Spark, streaming, Kafka-like systems, OLAP stores). 2. Experience in observability, user analytics, experimentation platforms, or reliability monitoring. 3. Familiarity with event correlation and change attribution (e.g., linking regressions to code/config/feature flag changes). 4. Experience building tools that improve workflow quality (onboarding, annotation, diagnosis dashboards). 5. Experience with Causal inference. Uber's mission is to reimagine the way the world moves for the better. Here, bold ideas create real-world impact, challenges drive growth, and speed fuelds progress. What moves us, moves the world - let’s move it forward, together. Offices continue to be central to collaboration and Uber's cultural identity. Unless formally approved to work fully remotely, Uber expects employees to spend at least half of their work time in their assigned office. For certain roles, such as those based at green-light hubs, employees are expected to be in-office for 100% of their time. Please speak with your recruiter to better understand in-office expectations for this role. \*Accommodations may be available based on religious and/or medical conditions, or as required by applicable law. To request an accommodation, please reach out to [accommodations@uber.com](mailto:accommodations@uber.com).