Hi, I'm Shobeir.

What I do now

I'm Executive Director of Data Science & ML Engineering at CVS Health, leading a 78-person organization — data science, decision science, ML engineering, and software engineering — behind personalization, offers, CRM, and retail media. Together that portfolio delivers about $300M in annual margin.

My job is turning manual, rules-driven operations into AI decision platforms, building the teams that run them, and tying every model to a measured business outcome. Today that means four platforms: the Offer Engine (personalized coupons for 90M+ customers), CRM, CVS Media Exchange, and Sparkle, an agentic insights engine for marketing and merchandising.

A few things I'm proud of

• CorIQ™ — I architected CVS's end-to-end agentic marketing platform, replacing spreadsheet-driven campaign ops with agentic data access, in-flight AI optimization, an audience engine, and omnichannel measurement. Campaigns scaled 4× with flat headcount; it was featured at Google Cloud Next 2026.
• The Offer Engine rebuild — redemption forecast error down from 10–15% to 1%, refresh cycle from 14 days to under 7, and optimization 7× faster and cheaper. Finance can now plan an $800M+ promotional budget with confidence.
• CorWin — self-service AI analytics that grew from 68 to 1,800 questions a month while accuracy climbed from 68% to 92%.
• CVS's first cross-business recommendation engine across CVS.com and the app (2B+ visits a year) — $27M in incremental margin and CVS Health's inaugural CTO Vibrancy Award.
• Experimentation as a default — 7.5× more tests a quarter at CVS, and 18× at Gopuff, where I built the platform from scratch.

How I got here

• CVS Health — Executive Director, Data Science & ML Engineering (2025–now); Director, Head of Retail Media Data Science at CMX (2023–2025); Director, Data Science & Personalization for CVS.com & App (2022–2023).
• Gopuff — Principal Data Scientist, Experimentation (2021–2022). Built A/B + switchback testing for a two-sided marketplace and an automated stats engine; 6 tests a quarter became 36 a month.
• Aetna, a CVS Health company — Senior Manager / Lead / Senior Data Scientist (2018–2021). Won the CVS Health enterprise venture competition with an NLP + speech product, raised clinical model recall from 65% to 92%, and co-founded the experimentation Center of Excellence.
• Verra Mobility — Data Scientist on revenue forecasting and pricing-behavior modeling (2017–2018).
• Arizona State University — Researcher & Instructor.

Outside the day job: member of the IAB AI Committee, conference reviewer for AMIA, Harvard Business Review Advisory Council, and formerly Lead Program Developer at Cheeky Scientist, mentoring PhDs into industry.

Before data science

I came in through the side door. PhD in Physical Chemistry (quantum mechanics) from Arizona State University — dissertation on molecular models for conductance in junctions and electrochemical electron transfer; M.Sc. in Physical Chemistry from Sharif University of Technology. Ten peer-reviewed papers, including computational work in JACS that helped discover a highly efficient nickel catalyst for hydrogen production. On the side I built AstroPaint, an open-source Python package for painting astrophysical signals onto sky maps. The quantum/astro detour shaped how I think about uncertainty, models, and what it means for a result to be "real."

What I'm into

Personalization, healthcare, experimentation, on-device AI, and small tools that turn a one-evening idea into something I can actually use. ai, may I? is the place I keep those experiments — illustrated public-domain classics retold with AI, a card-stitcher for scanned greetings, an on-device photo organizer (Glimp), and whatever's next.

Outside of all that, I draw and paint. @ink.visions is the visual journal.

Get in touch

If something here resonates — collaboration, a question about the work, a role in AI, personalization, or decisioning — sh.seddigh@gmail.com is the fastest way to reach me. LinkedIn works too.