Data Scientist with Python expertise in New York

Job Description

Key Responsibilities

• Build and maintain multi-touch attribution (MTA) models - touch-order aware, channel-weighted, with incremental lift quantification across owned, paid, and clean room channels
• Develop cohort-level LTV/CAC scoring models using transaction signals, behavioral features (SHAP-ranked), and propensity scores - deployed at segment and micro-cohort resolution
• Design holdout and matched-market test frameworks for measuring incrementality across CTV, display, paid search, and social channels
• Build probabilistic identity linkage models for household graph construction and cross-device resolution where deterministic signals are absent
• Develop SHAP-based feature importance pipelines for audience signal ranking - surfacing top predictive signals per segment for AI-generated audience briefs
• Build behavioral micro-cohort clustering using unsupervised and semi-supervised methods on transaction and lifestyle features - producing 10+ interpretable sub-cohorts per major audience segment
• Design suppression, exclusion, and lookalike model pipelines that feed into DSP activation and clean room audience delivery
• Collaborate with engineering to design system prompts, structured output schemas, and evaluation frameworks for AI-powered audience authoring, measurement intelligence, and campaign brief generation
• Build model evaluation pipelines comparing AI-generated audience segments against held-out conversion actuals, benchmarking performance vs. deterministic baselines
• Develop geo-level DMA performance models: LTV/CAC opportunity mapping, state-vs-DMA benchmarking, and priority zone classification for campaign planning
• Author AI-assisted insight narratives - translating model outputs into plain-language recommendations surfaced to client marketing teams through the platform UI

Required Qualifications

• 5+ years applied data science experience
• Expert Python proficiency: scikit-learn, XGBoost or LightGBM, SHAP, pandas, statsmodels, and at least one deep learning framework for production model development
• Deep expertise in multi-touch attribution methodologies: MTA, media mix modeling (MMM), incrementality testing, and controlled experiment design
• Experience building LTV, propensity, and CAC models on financial transaction or behavioral data at segment and sub-segment resolution
• Comfort operating inside data clean rooms - designing models that run on privacy-preserving aggregates rather than individual-level raw data
• Strong statistical foundations: causal inference, Bayesian methods, survival analysis, and experiment design
• Fluent SQL across cloud data warehouses (Snowflake, BigQuery, Redshift, or equivalent) and experience working with ML platforms such as Vertex AI, SageMaker, or Databricks MLflow
• Ability to translate complex model outputs into business narratives for VP- and C-level marketing stakeholders

Preferred Qualifications

• Experience designing AI-augmented analytics workflows - using LLM APIs for structured output generation, signal summarization, or compliance pre-screening alongside traditional models
• Familiarity with walled garden measurement environments: Google ADH, Meta Analytics API, Amazon Attribution
• Graph-based modeling experience - using Neo4j, Amazon Neptune, or similar for identity linkage, co-purchase signals, or household relationship modeling
• Demonstrated expertise in identity resolution, household modeling, or cross-device attribution at scale

Pay

The base compensation range for this role in the posted location is: $100,000 to $130,000.

Benefits

• Paid time off based on employee grade (A-F)
• Medical, dental, and vision coverage (or provincial healthcare coordination in Canada)
• Retirement savings plans (e.g., 401(k) in the U.S., RRSP in Canada)
• Life and disability insurance
• Employee assistance programs
• Other benefits as provided by local policy and eligibility