New York, NY ·


Summary

Analytics engineer with 7+ years building canonical data models, semantic-layer infrastructure, and AI-native analytics workflows across healthcare and fintech startups. Currently leading billing data architecture and a company-wide semantic layer migration at Pelago Health. Excited to apply this foundation to building trustworthy, scalable analytics infrastructure for AI products.


Professional Experience

Pelago Health (formerly Quit Genius) | Analytics Engineer | May 2024 – Present

New York, NY · Reports directly to CFO · Virtual specialty substance use clinic serving employers and health plans.

  • Re-architected Pelago’s billing data platform from a monolithic dbt pipeline into a modular, snapshotted intermediate-model system with layered dbt tests and lineage documentation — powering enterprise billing workflows across 10+ clients. Partnered with data engineering to orchestrate upstream ingestion through Airflow DAGs, establishing canonical billing datasets serving Finance, Operations, Product, and GTM reporting.

  • Led company-wide migration strategy from Looker to Cube semantic-layer architecture to standardize metric definitions, enable governed self-serve analytics across 14 business domains, and ground LLM-assisted querying workflows in a trusted metric layer.

  • Built and shipped an AI-assisted analytics QA and incident-routing pipeline integrating dbt, Elementary, Slack, Claude, and Jira. The system detects billing data anomalies, generates LLM-grounded failure summaries from dbt manifest and model lineage, and auto-routes triaged tickets to the right owner — replacing manual on-call inspection and significantly reducing time-to-triage on billing incidents.

  • Partnered with GTM teams (Sales, Customer Success, Marketing) to define and instrument funnel, account-health, and member-engagement metrics; owned the Member Strategy Dashboard end-to-end and contributed to the multi-phase Member Journey Dashboard used by executive leadership to monitor member activation, care initiation, treatment engagement, and retention.

  • Built within-member engagement anomaly detection models using rolling z-score baselines against behavioral signals, translating qualitative clinical-operations heuristics into scalable, data-driven prioritization workflows.


Level | Data Analyst → Data Scientist | February 2021 – December 2024

New York, NY · B2C fintech offering embedded card products and dental benefits.

Data Scientist (Part-time Contract) · May 2024 – December 2024

  • Partnered with Product, Operations, and Risk to formalize fraud and payments-risk data into standardized metrics and operational reporting; explored transactional and fraud-behavior datasets in Python and Jupyter to support risk-program analytics.

Data Analyst, promoted to Data Scientist · February 2021 – January 2024

  • Built and maintained production dbt pipelines transforming nested transactional and protobuf-based payments data into documented canonical models for product analytics, risk monitoring, operational reporting, and experimentation.

  • Developed reusable Jinja macros to convert protobuf-derived JSON blobs into structured BigQuery data models used across multiple analytics domains — reducing model development time and enforcing consistent data definitions.

  • Led enterprise BI migration from Periscope to Looker/LookML, designing reusable semantic definitions and enabling scalable self-serve analytics across Product, Engineering, Operations, and non-technical business teams; ran enablement sessions and office hours to accelerate adoption.

  • Defined success metrics for Product and Engineering roadmap initiatives, identifying key levers for increasing card utilization and reducing operational burden; partnered with stakeholders to translate data requirements into actionable insights.

  • Implemented custom Python ETLs to extract third-party API data for exploratory analysis in Jupyter Notebooks, including developing and evaluating risk rules using statistical performance metrics on fraud-related features.


Crossix, A Veeva Company | Senior Analyst, Marketing Analytics | June 2019 – January 2021

New York, NY

  • Owned 30+ end-to-end analyses evaluating life-sciences marketing impact on healthcare behaviors using privacy-safe claims, EHR, and prescription-drug datasets — delivering actionable, scalable campaign recommendations to pharmaceutical clients.

  • Identified operational inefficiencies and designed troubleshooting workflows and tooling improvements as part of an internal operational analytics working group.

  • Ingested, explored, and packaged COVID-19 marketing-trend data for client workshops and industry-facing content.


New York State Department of Health AIDS Institute | Digital Health Initiatives Intern | January 2018 – June 2019

New York, NY

  • Built web-scraping pipelines and performed quantitative and qualitative analysis in R (tidyverse, ggplot, sentiment analysis) on 500+ social media comments to evaluate engagement for a HRSA-funded HIV intervention; instrumented Google Analytics on the program website.

  • Developed and led presentations on new tools and technologies for digital health program promotion.


Columbia University Mailman School of Public Health | Lerner Center Research Fellow | June – December 2018

New York, NY

  • Coded and analyzed point-of-sale advertising survey data for tobacco products across New York City retailers.

  • Contributed to research design, survey instruments, and policy reviews for a study on social media advertising of cannabis vaporizer products; supported manuscript development for publication.


Skills

  • Analytics Engineering: dbt (advanced), Cube, Looker/LookML, semantic layer design, canonical data modeling, data lineage documentation, dbt testing and alerting (Elementary)
  • Data Infrastructure: Airflow, AWS Redshift, S3, Datafold, BigQuery, Postgres, ETL/ELT pipeline design
  • Languages: SQL (expert), Python (pandas, numpy, statsmodels, sklearn), R (tidyverse, ggplot), Jinja
  • AI-Native Workflows: LLM-integrated analytics pipelines, Claude, Claude Code, Cursor
  • Other: Git/GitHub, Jupyter, self-serve analytics enablement, cross-functional stakeholder partnership (GTM, Product, Engineering, Finance)

Education

Master of Public Health | Columbia University Mailman School of Public Health

  • Concentration: Sociomedical Sciences
  • Certificate: Applied Biostatistics
  • Award: Dr. Jack Elinson Scholarship Recipient
  • Thesis: How Data Determines Health: A Qualitative Research Proposal Exploring Perceptions of Big Data in Public Health

Bachelor of Science, Cognitive Science (Specialization in Computing) | University of California, Los Angeles

  • Graduated Magna Cum Laude · Dean’s Honors List

Publications

  • Spillane, T.E., Wong, B.A., Giovenco, D.P. (2020). Content analysis of Instagram posts by leading cannabis vaporizer brands. Drug and Alcohol Dependence. https://doi.org/10.1016/j.drugalcdep.2020.108353

  • Giovenco, D.P., Spillane, T.E., Wong, B.A., Wackowski, O.A. (2019). Characteristics of storefront tobacco advertisements and differences by product type. Preventive Medicine, 123, 204–207.


Hackathons

Open Climate Collabathon 2019 | Consumer Disclosure Team | December 2019

  • Won Community Choice and Most Innovative Contribution awards.
  • Designed a “sustainability score” framework for grading consumer product supply chains and contributed to a proof-of-concept browser extension to surface those scores on retail websites.

DataKind + Microsoft Virtual DataDive: Applying AI to Societal Challenges | Miami Project | October 2019

  • Collaborated with volunteer data scientists and the Code for Miami organization to apply AI to affordable housing.
  • Conducted exploratory data analysis in R and Python; helped build and evaluate ML models and stood up an API to identify variables driving turnaround time for affordable housing applications.

Mount Sinai Health Hackathon 2019 | Team Blackbox AI | October 2019

  • Designed and built a prototype website using Dash (Python) to educate clinicians on the application and interpretation of AI in healthcare settings, incorporating interactive statistical visualizations and written explainers.