Senior Data Scientist,Digital

Senior Data Scientist Job Description 

As a Senior Data Scientist, you will lead the end-to-end development of intelligent systems that optimize digital campaign performance across channels within IQVIA’s Media OS platform. You will transform complex, multi-source campaign, audience, engagement, conversion, cost-efficiency, and ROI data into scalable predictive scoring, ranking, recommendation, and decisioning solutions that improve platform selection, targeting, budget allocation, engagement, and conversion outcomes. While this role is primarily focused on data science, you will also be responsible for hands-on data engineering tasks as needed, including building and optimizing data pipelines, workflows, training datasets, and production data integrations. You will work at the intersection of machine learning, experimentation, data engineering, and production decision systems while collaborating with product managers, data engineers, software engineers, analysts, and IQVIA healthcare and ad tech domain experts. 

Essential Functions 

• Analyze campaign performance across platforms and channels, including impressions, audience engagement, conversions, cost efficiency, ROI, lift, and incrementality. 

• Lead the design, development, validation, deployment, and optimization of predictive scoring, ranking, recommendation, personalization, and machine learning solutions for platform effectiveness, audience targeting, campaign planning, activation, budget allocation, and measurement. 

• Perform exploratory analysis and feature engineering on complex relational and multi-channel datasets, including campaign data, audience behavior, engagement signals, identity attributes, and healthcare and life sciences data. 

• Apply gradient boosting, learning-to-rank, statistical modeling, causal inference, uplift modeling, attribution methods, and optimization techniques to improve campaign and platform decisions. 

• Design and analyze A/B tests, holdouts, and other controlled experiments; define hypotheses, success metrics, evaluation frameworks, and business-impact measures. 

• Build, maintain, and optimize scalable batch and real-time data pipelines, workflows, training datasets, and feature pipelines that support analytics, audience forecasting, model development, and production inference within IQVIA’s Media OS platform. 

• Perform backend data engineering work as needed, including data modeling, warehouse design, pipeline troubleshooting, performance optimization, and integration of multi-source data across cloud environments. 

• Evaluate and implement generative AI and emerging AI capabilities, including large language models, retrieval-augmented generation, vector search, prompt engineering, and agentic workflows, where they provide measurable and responsible platform value. 

• Establish reproducible data science and MLOps practices for testing, documentation, versioning, CI/CD, deployment, monitoring, drift detection, retraining, and continuous improvement of model accuracy and business impact. 

• Ensure the quality and reliability of both model and data pipeline code through peer reviews, automated testing, documentation, monitoring, and adherence to shared architectural and coding standards across global engineering pods. 

• Apply IQVIA standards for privacy, security, model governance, explainability, fairness, and responsible AI when working with healthcare, life sciences, and advertising data. 

• Communicate analytical methods, findings, limitations, and actionable recommendations clearly to technical, product, and business stakeholders; mentor junior data scientists and promote consistent technical standards. 

Qualifications 

Required: 

• Master’s or PhD in Data Science, Computer Science, Statistics, Applied Mathematics, Engineering, or a related quantitative field; a bachelor’s degree with substantial relevant experience may also be considered. 

• Strong foundation in machine learning, statistics, probability, data analysis, predictive modeling, model validation, and experimental design. 

• Advanced proficiency in Python and SQL, with hands-on experience using pandas, NumPy, scikit-learn, and related data science libraries. 

• Demonstrated ability to perform production data engineering tasks, including developing and optimizing data pipelines and workflows, working with large relational datasets, and applying data warehousing concepts. 

• Hands-on experience with cloud data platforms, preferably Google Cloud or AWS, and data warehouse technologies such as BigQuery, Snowflake, or comparable platforms. 

• Hands-on experience designing, implementing, deploying, monitoring, and maintaining machine learning models in production. 

• Demonstrated proficiency with gradient boosting models for predictive scoring, including XGBoost, LightGBM, CatBoost, or comparable frameworks. 

• Experience with ranking models or learning-to-rank approaches and appropriate ranking evaluation metrics. 

• Experience performing feature engineering on complex relational, multi-source, or multi-channel datasets. 

• Experience analyzing marketing, advertising, campaign performance, audience, or customer engagement data and connecting model outcomes to business metrics. 

• Proficiency with software engineering and MLOps practices, including Git, code review, automated testing, modular design, documentation, CI/CD, model versioning, and monitoring. 

• Strong analytical thinking, structured problem-solving, and written and verbal communication skills, with the ability to translate ambiguous business needs into scalable data science solutions. 

Preferred: 

• Experience building recommendation systems, personalization models, propensity models, or decision systems that optimize targeting, platform selection, or resource allocation. 

• Familiarity with multi-channel campaign ecosystems, programmatic advertising, ad tech, marketing technology, audience segmentation, media activation, attribution, forecasting, and campaign optimization. 

• Knowledge of causal inference, attribution modeling, incrementality analysis, uplift modeling, A/B testing, and experimental design. 

• Broader experience across Google Cloud, AWS, or Azure, including cloud-based data, orchestration, and machine learning services. 

• Familiarity with modern data platforms and distributed-processing tools such as Snowflake, Spark, and Databricks. 

• Experience mentoring junior data scientists, data engineers, or contractors and helping teams apply consistent technical and architectural standards. 

• Experience creating decision-oriented visualizations or dashboards with Tableau, Power BI, or comparable business intelligence tools. 

• Experience developing generative AI applications using LLM APIs, embeddings, retrieval-augmented generation, vector databases, evaluation frameworks, or agent orchestration. 

• Healthcare, life sciences, healthcare claims, or privacy-enhanced data experience, including an understanding of responsible use and regulated-data considerations.