• Develop and deploy advanced Machine Learning models focused on CRM (including customer segmentation, churn prediction, LTV calculation, and recommendation systems); • Conduct statistical analyses, A/B tests and experiments to evaluate CRM initiatives and strategies; • Collaborate with Product, CRM, Marketing and Engineering teams to define problems, propose solutions and communicate results clearly; • Build and manage data pipelines, applying MLOps practices to ensure scalable, reliable and secure solutions; • Promote the use of Generative Artificial Intelligence (GenAI/LLMs), integrating it across the project lifecycle — from planning to development and delivery; • Mentor junior data scientists and promote best development practices; • Stay up to date with the latest trends and advances in Data Science, Machine Learning and AI, with a special focus on CRM applications.

• Propose, plan, and execute applied research initiatives that will make a real-world impact on Conversational AI using Large Language Models (LLMs) within a commercial setting. • Use expert knowledge of Transformer architecture mechanics (Attention, Tokenization, Embeddings) to consistently find the most effective, efficient, stable, explainable, and elegant prompting and orchestration approaches. • Utilize modern LLM inference and retrieval pipelines. • Analyze large scale conversational datasets for RAG (Retrieval-Augmented Generation) optimization. • Bring research-inspired prompt strategies to life within production systems. • Create durable, flexible scientific evaluation and experimentation capabilities for non-deterministic model outputs. • Present findings on model behavior and context efficacy in ways that inform and guide business and product strategy. • Work closely with other scientists. • Stay current with the rapidly evolving state of Generative AI.

This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more. Role Description The Data Scientist is responsible for applying advanced analytics, statistical modeling, and machine learning techniques to support strategic decision-making across the organization. This role partners closely with stakeholders in Underwriting, Actuarial, Claims, Product, Revenue, and Customer Experience to translate business questions into analytical solutions that improve operational performance, risk evaluation, and customer outcomes. - Develop predictive models, explore new data sources, and generate actionable insights that support pricing, underwriting, claims management, and operational efficiency. - Contribute to the development and operationalization of models and analytics solutions by working with engineering and product teams to integrate insights into business tools, dashboards, and workflows. Qualifications - Bachelor's degree in data science, Statistics, Mathematics, Computer Science, Economics, or a related quantitative field required. - Advanced degree (MS or PhD) preferred. - 3 - 7 years of experience in data science, advanced analytics, or statistical modeling roles. - Experience working with large datasets and complex analytical problems. - Strong programming skills in Python and SQL. - Experience with statistical modeling and machine learning techniques. - Experience with data visualization and analytical tools (e.g., Tableau, Power BI, Looker, or similar). - Ability to translate complex analytical findings into clear business insights. - Strong problem-solving and critical thinking skills. - Ability to collaborate effectively with both technical and non-technical stakeholders. Requirements - Partner with stakeholders across Underwriting, Actuarial, Claims, Product, and Revenue to identify opportunities where data can inform better business decisions. - Translate business questions into analytical frameworks, hypotheses, and statistical approaches. - Analyze customer, broker, and operational data to identify trends, anomalies, and opportunities to improve engagement, retention, and operational performance. - Conduct exploratory data analysis to investigate business problems and generate actionable insights. - Communicate analytical findings through visualizations, dashboards, and written summaries. - Develop predictive models and statistical analyses to support pricing, underwriting, claims, reserving, and operational initiatives. - Apply machine learning techniques including regression, classification, clustering, and other statistical learning methods to solve complex business problems. - Evaluate model performance and continuously improve models based on new data and changing business needs. - Explore internal and third-party data sources to enhance model performance and uncover new insights. - Collaborate with engineering and product teams to deploy analytical models into production systems and operational workflows. - Support the implementation of MLOps practices, including model versioning, deployment pipelines, monitoring, and lifecycle management. - Monitor models for performance degradation, bias, or drift and implement improvements as needed. - Document model assumptions, methodology, and validation processes to support transparency and governance. - Contribute to the improvement of internal data infrastructure, ETL pipelines, and reporting architecture. - Support the development and optimization of dashboards and analytics tools used by business teams. - Ensure data quality, consistency, and reliability across analytical workflows. - Identify opportunities to automate recurring analyses and reporting processes. - Work closely with business stakeholders to ensure analytics solutions align with operational needs and strategic objectives. - Partner with product and engineering teams to integrate analytical capabilities into internal platforms and decision tools. - Provide analytical support for ad-hoc requests and strategic initiatives. - Other duties as assigned. Benefits - Flexible PTO - Generous parental and caregiver leave - 401K match - Excellent medical, dental, and vision plans - Remote-first culture - Annual $1000 tuition reimbursement stipend - And more!

• Translate business requirements into technical specifications, data models, data streams, and databases • Develop production ready geospatial workflows and data pipelines using open-source python libraries • Work with online transaction processing (OLTP) and online analytics processing (OLAP) stacks (PostgreSQL, DuckDB, PyArrow, Parquet / GeoParquet) • Develop spatial computation with H3, Shapely, GDAL/OGR and other lightweight geospatial utilities • Write testable, benchmarked code using pytest and async test patterns • Build with python package managers like uv and poetry utilizing pyproject.toml for project management • Collaborate in open-source–style repositories with linting, formatting, typing, and CI expectations • Build CI/CD pipelines with integrated unit tests • Convert or embed ML/AI workflows into production-grade, enterprise systems • Utilize Research, Plan, Implement strategies for AI-driven development practices • Design, develop, and maintain infrastructure for geospatial analysis and ML/AI applications on large data.