Data Science Engineer

• Design, develop, validate, and deploy machine learning models for marketing forecasting, campaign estimation, media planning, and budget optimization.
• Build marketing response models incorporating response curves, diminishing-returns analysis, marginal efficiency, and budget allocation recommendations.
• Develop time-series forecasting, resource estimation, predictive modeling, and Generative AI solutions, including LLM agents, retrieval systems, MCP servers, and entity resolution workflows.
• Own the end-to-end machine learning lifecycle, including feature engineering, production deployment, monitoring, versioning, drift detection, retraining, and model evaluation.
• Build and maintain production ML pipelines with Apache Airflow and Python services; collaborate with stakeholders to communicate modeling assumptions, results, and recommendations.

• Design, develop, validate, and deploy machine learning models for marketing forecasting, campaign estimation, media planning, and budget optimization.
• Build marketing response models incorporating response curves, diminishing-returns analysis, marginal efficiency, and budget allocation recommendations.
• Develop time-series forecasting, resource estimation, predictive modeling, and Generative AI solutions, including LLM agents, retrieval systems, MCP servers, and entity resolution workflows.
• Own the end-to-end machine learning lifecycle, including feature engineering, production deployment, monitoring, versioning, drift detection, retraining, and model evaluation.
• Build and maintain production ML pipelines with Apache Airflow and Python services; collaborate with stakeholders to communicate modeling assumptions, results, and recommendations.

• Demonstrated experience developing and deploying machine learning solutions for marketing analytics, forecasting, estimation, or media optimization.
• Advanced Python skills with pandas, Num Py, scikit-learn, and stats models, plus strong SQL and data warehouse experience.
• Strong foundation in statistics, experimentation, uncertainty quantification, backtesting, model validation, and forecasting or probabilistic modeling using tools such as Prophet, PyMC, or Stan.
• Hands-on experience managing production ML pipelines and the complete ML lifecycle, including deployment, monitoring, data quality checks, and retraining with Apache Airflow.
• Experience building Generative AI solutions, including MCP servers, LLM agents, tool-calling workflows, prompt engineering, structured outputs, LLM evaluation, embeddings, vector databases, RAG, or entity resolution.

• Machine Learning
• Marketing Analytics
• Forecasting
• Python
• Statistical Modeling
• Apache Airflow
• Generative AI
• LLM Agents
• Retrieval-Augmented Generation
• Model Monitoring

Hourly rate is commensurate with experience and is an estimated range provided by Work Genius.