Data Scientist bei TEGNA Inc.

TEGNA Inc. (NYSE: TGNA) helps people thrive in their local communities by providing the trusted local news and services that matter most. With 64 television stations in 51 U.S. markets, TEGNA reaches more than 100 million people monthly across the web, mobile apps, streaming, and linear television. Together, we are building a sustainable future for local news.

Role Overview
We are seeking a versatile Data Scientist to lead end-to-end modeling and insights for a multi-platform media ecosystem spanning linear TV, digital, web, social, streaming, and apps. You will transform rich viewership, content, and sales datasets into predictive models, optimization frameworks, and actionable insights that shape content strategy, audience growth, and advertising performance. Ideal candidates are adaptable thinkers who enjoy exploring ambiguous problems, can craft clear narratives from complex data, and bring fresh, creative approaches to a fast-evolving media landscape.

Responsibilities:
What You’ll Do

• Own the full data science lifecycle: problem framing, hypothesis design, feature strategy, model development, validation, deployment planning, and impact measurement.
• Build audience and engagement models using multi-source viewership and behavioral signals (e.g., forecasting, churn/retention, cross-platform attribution, time-series and panel-based analysis).
• Develop content intelligence with NLP: taxonomy/labeling, semantic similarity, topic and entity modeling, summarization, quality/relevance scoring, content-to-audience matching, and trend detection.
• Create sales and advertising analytics: demand forecasting, pricing/revenue optimization, propensity and uplift modeling, inventory allocation, and campaign effectiveness measurement.
• Design interpretable measurement frameworks: incrementality tests, controlled experiments, uplift/A/B testing, holdouts, and causal inference for content and ads.
• Unify cross-platform metrics to produce holistic funnels and KPIs; define leading indicators and build early-warning/nowcasting approaches for performance health.
• Engineer robust features from logs, sessions, sequences, and text; handle seasonality, cold start, sparsity, and platform-specific biases.
• Establish model governance: backtesting, stability monitoring, drift detection, fairness and bias assessment, and clear documentation of assumptions and limitations.
• Translate complex results into clear, executive-ready narratives; deliver recommendations that drive editorial, product, growth, and revenue decisions.
• Partner with editorial, product, sales, and audience teams to prioritize high-leverage opportunities and design data-informed roadmaps.
• Mentor teammates, elevate analytical rigor, and promote a culture of curiosity, experimentation, and measurable impact.

Core Skills and Methods:

• Statistical modeling and inference: generalized linear models, hierarchical/mixed effects, survival/retention analysis, causal inference (matching, diff-in-diff, instrumental variables where appropriate).
• Forecasting and demand modeling: univariate/multivariate time series, seasonality and event effects, hierarchical reconciliation, anomaly detection, and nowcasting.
• Machine learning for structured data: classification, regression, ranking, uplift modeling, and ensemble methods; strong emphasis on feature engineering and interpretability.
• Natural language processing for media: text normalization, embeddings, topic modeling, entity and key-phrase extraction, similarity search, content clustering, and evaluation of relevance/quality.
• Experimentation and measurement: A/B and multivariate testing, power analysis, sequential testing safeguards, uplift/causal experimentation, incrementally for ads and content.
• Optimization and decisioning: inventory and pricing optimization, budget allocation, scheduling/lineup optimization, and portfolio trade-off analysis.
• Data acumen: wrangling complex, high-volume, multi-platform datasets; designing reliable labels and ground truth; handling sparsity, delayed feedback, and feedback loops.
• Model evaluation and monitoring: rigorous offline/online validation, business-aligned metrics, calibration, stability, drift and leakage checks, and post-deployment learning.
• Communication and influence: concise storytelling with data, stakeholder alignment, and the ability to convert insights into concrete actions and tests.

Requirements:

• What Makes You a Great Fit:
• 5+ years of applied data science experience delivering measurable impact in consumer, media, advertising, or adjacent domains.
• Proven track record building models from viewership, content, and sales datasets, with shipped or adopted solutions that informed programming, growth, or revenue.
• Comfort navigating ambiguity, quickly forming hypotheses, and iterating toward practical, high-signal solutions.
• Balanced mindset across rigor and speed: you know when to prototype, when to harden, and how to quantify trade-offs.
• Strong collaboration skills and curiosity about how editorial, product, growth, and sales teams operate and make decisions.
• Commitment to responsible modeling: transparency, fairness, and clearly communicated limitations and risks.
  
  Impact You’ll Drive:
• Clear, cross-platform understanding of audience behavior and content performance.
• Faster, smarter decisions on what to make, when to publish, where to distribute, and how to monetize.
• Better return on advertising through improved forecasting, allocation, and incrementality measurement.
• Scalable frameworks for experimentation, measurement, and continuous learning across the organization.
  
  Preferred:
• Candidates with advanced degrees in the field of Data Science, NLP or similar.
• Candidates with prior experience working in Media or Content.