• Design, build, and maintain forecasting and optimization models embedded in core product workflows • Model behaviors, impacts of weather, and behind the meter resources • Translate operational and business requirements into quantitative frameworks and production systems • Own the full lifecycle of quantitative systems — from data ingestion and feature development through deployment, monitoring, and reliability in production environments • Design and maintain data pipelines, schemas, and interfaces that support production forecasting and optimization workflows • Establish best practices for model development, validation, performance monitoring, and operational robustness • Partner closely with engineering to define interfaces, data contracts, and system boundaries that enable robust quantitative services • Provide technical leadership and guidance on quantitative methods across the organization

• Lead end-to-end monitoring of underwriting model performance and outcomes, ensuring models are behaving as expected across risk segments and macroeconomic conditions; translate model metrics into clear business implications • Detect shifts in approval rates, loss performance, borrower behavior, or model predictions, and use analytical methods to investigate drivers of change, distinguish signal from noise, and quantify business impact • Apply statistical techniques to assess A/B tests, model launches, and natural experiments, and provide clear recommendations grounded in causal reasoning and quantitative evidence • Develop and maintain automated reporting, monitoring frameworks, and workflows that ensure timely, accurate visibility into model performance at scale

• 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.