Data Scientist

About the Role In this role, you will design and implement machine learning (ML) and natural language processing (NLP) solutions to support risk and incident analytics. You will partner with cross-functional stakeholders to build models that identify high-risk events, predict claim severity, and generate explainable insights that enable faster, data-driven decision-making. Your work will directly impact how organizations mitigate risk and improve operational outcomes. Responsibilities • Translate ambiguous business problems into clearly defined data science solutions aligned with measurable KPIs. • Design, build, and deploy machine learning models for incident prioritization, claim prediction, and severity classification. • Develop feature engineering pipelines using structured and unstructured data sources. • Apply NLP techniques to extract insights from incident and claim narratives. • Implement record linkage methods to connect related datasets without clean unique identifiers. • Build and validate predictive models to assess risk likelihood and financial impact. • Generate explainable outputs, including key drivers and interpretable insights for business users. • Partner with cross-functional teams including Risk, Legal, Engineering, Analytics, and Governance to deliver scalable solutions. • Monitor model performance, data drift, and system reliability; iterate and retrain models as needed. • Document methodologies, assumptions, and validation results to ensure reproducibility and transparency. • Ensure compliance with data governance standards, including proper handling of sensitive data. • Communicate insights and recommendations to technical and non-technical stakeholders. • Mentor junior team members and contribute to a culture of continuous learning and innovation. Minimum Qualifications • Master’s degree in Computer Science, Statistics, Industrial Engineering, or a related technical field, or equivalent practical experience. • 5+ years of experience in data science, machine learning, or operations research (or 2+ years with a PhD). • Experience building and deploying ML models using Python and SQL. • Experience with feature engineering, model evaluation, and optimization techniques. • Experience working with large-scale data processing frameworks (e.g., Spark). Preferred Qualifications • PhD in a quantitative field. • Experience with operations research methods (e.g., linear programming, mixed-integer programming) and related tools. • Experience with NLP and text analytics. • Experience working with cloud platforms (e.g., AWS, Azure, or GCP). • Familiarity with MLOps, CI/CD pipelines, and production model monitoring. • Experience with streaming or real-time data systems. • Strong understanding of data governance and responsible AI practices. • Ability to translate complex analytical results into business impact. • Excellent communication and collaboration skills. Rate: $75-$100/hr