Head of Data Science, AI-Driven Behavioral Embeddings

Jobtome; Carlstadt (NJ); On-site; USD 263,000 - 394,000; Full time

Job summary

Spectrum is seeking a Head of Data Science to lead the development of transformer-based embeddings and predictive models that power audience, insights, and measurement products. You’ll own the embedding roadmap, drive evaluation standards, and collaborate with product, sales, and partners to scope pilots and convert evaluations into contracts.

You will build and grow a data science team, establish MLOps and responsible AI practices, and ensure models meet commercial and regulatory standards

Qualifications

• Proven record leading data science for data, audience, identity, targeting, or measurement products in advertising/marketing ecosystems.
• Hands-on predictive modeling on consumer-level data at scale (propensity, segmentation, lookalikes).
• Knowledge of measurement/causality: incrementality, controls, test-and-holdout design.
• Experience with identity graphs, on-boarding, clean rooms, and licensed third-party data in modeling.
• Lifecycle of ML in production: feature stores, scoring pipelines, monitoring.

Responsibilities

• Build and lead predictive models behind audience and data products across multiple verticals.
• Lead the platform's Feature Store as a commercial product with documented features.
• Oversee audience and lookalike modeling, including seed-based and CRM-based approaches.
• Define evaluation methodology with bias, fairness, and calibration considerations.
• Lead the data science roadmap for transformer-based embedding models and related architectures.
• Set standards for MLOps, release gates, drift monitoring, and privacy-preserving techniques.
• Engage with customers and partners to translate methodology into commercial proof points.
• Grow and mentor a high-performing data science team, prioritizing production impact.

Skills

Leadership of data science teams

Predictive modeling at scale

Measurement & causal inference

Identity & data collaboration

Production ML lifecycle & featureStore

Python, SQL, distributed processing

Deep learning & embeddings/transformer

Privacy-preserving analytics

Communicating methodology to execs

Hiring senior data science talent

AI applications in consumer intel

Education

Bachelor’s Degree in Computer Science, Statistics, Mathematics, Economics, or related quantitative field

Tools

Snowflake

LiveRamp

AWS

Databricks

Spark

Job description

Spectrum is seeking a Head of Data Science to lead the development of transformer-based embeddings and predictive models that power audience, insights, and measurement products. You’ll own the embedding roadmap, drive evaluation standards, and collaborate with product, sales, and partners to scope pilots and convert evaluations into contracts.

You will build and grow a data science team, establish MLOps and responsible AI practices, and ensure models meet commercial and regulatory standards