AI-native Product Data Scientist owning measurement + evaluation loops for Wearables GenAI/CoreUX—driving phone-replacement adoption, task success, and retention across 10+ product teams.

▸ Defined Phone Replacement Rate as the org-level north star for phone-free high-value tasks (media, capture, comms, navigation); built event taxonomy + logging spec and launch governance, raising coverage 0%→90% for consistent cross-feature measurement. Holdout analysis showed users reaching ≥3 phone-free successful tasks have +5pp D7 retention since activation, informing roadmap priorities.

▸ Built an LLM-judge labeling framework for 15 voice-initiated actions (~50K/week), generating success/failure + failure taxonomy with QC via 3% spot-check + adjudication. Published a recurring quality report as the measurement standard for roadmap decisions, driving root-cause fixes (routing, vocabulary) and boosting task success +20pp.

▸ Led analytics for LiveAI (camera-based multimodal assistant); ran use-case mining + retention analysis across ~3K daily sessions to surface repeat-use scenarios and drive PMF improvements for a major 2025 GTM campaign. Defined latency + reliability metrics and built a monitoring dashboard; insights drove a 2-month launch delay to reach 99% reliability readiness.

▸ Designed pillar-level experimentation governance (hypotheses, success/guardrail metrics, readout standards) across 10 CoreUX & Inputs engineering teams, reducing coordination overhead and preventing cherry-picking. Drove launch decisions across Wearables: 10 launches and 5 pivots.

Policy-driven analytics to support high-profile, high-stakes legislative, regulatory, and legal efforts and decision-making, ensuring smooth operations across EMEA, APAC, and NORAM.

𝗣𝗼𝗹𝗶𝗰𝘆 𝗔𝗻𝗮𝗹𝘆𝘁𝗶𝗰𝘀: Developed statistical models to assess the impact of urban policies, such as Amsterdam's road closure program, and evaluated Uber's market coverage in the US and UK using both internal and external data sources.

𝗥𝗲𝗴𝘂𝗹𝗮𝘁𝗼𝗿𝘆 𝗖𝗼𝗺𝗽𝗹𝗶𝗮𝗻𝗰𝗲: Guided Uber's data collection strategy to meet French government requirements and designed automated data solutions for EU DMA legal requests, significantly reducing reporting time.

𝗟𝗲𝗮𝗱𝗲𝗿𝘀𝗵𝗶𝗽 & 𝗜𝗻𝗻𝗼𝘃𝗮𝘁𝗶𝗼𝗻:

▸ Led a project and presented to CEO Dara Khosrowshahi on behalf of Women@Uber in the Global Safety Think Tank Challenge.

▸ Awarded "Most Innovative" in the Go-Get-Zero 2023 competition for designing a zero-emission future.

Empowered better transportation systems across the Bay Area using data. Key clients included the SF government, real estate developers, and big tech companies.

Selected Work:

▸ Conducted causal analysis on the impact of streetscape changes on emergency vehicle travel speed, utilizing over 3 million observational data points. Employed Difference-in-Difference and Regression Discontinuity Design to address confounding variables, enhancing accuracy over conventional regression models.

▸ Applied K-means algorithm to identify 10 clusters across 287 ZIP codes based on residents' commuting patterns, improving model forecasting efficacy.

▸ Developed a web application using Streamlit with an interactive user interface, allowing clients to customize forecast tasks on vehicle miles commuted in response to different policies and commuting programs.

▸ Independently designed and created company website using Figma

▸ Designed infographics to communicate company mission and user journey

▸ Formulated graphic visualization strategies to optimize marketing/branding effectiveness

▸ Authored the company’s design blog in Medium and promoted Zenport brand

▸ Visualized and communicated cluster analysis process grouping different levels of autism, under the direction of Ognjen Rudovic