Senior Data Scientist - Credit Underwriting

About the Role

As a Senior Data Scientist on Clair’s Data Science team, you’ll be responsible for developing and maintaining the next generation of credit models and predictive systems that power Clair’s financial products. You’ll shape how millions of hourly workers access affordable credit, leveraging cutting-edge data science to assess risk, predict repayment, and optimize credit decisions.

We’re looking for someone who thrives at the intersection of data science, machine learning, and fintech, and who’s excited to translate messy, real-world data into clear, actionable intelligence. This role blends credit modeling with feature engineering — from designing new model features (including predictive features) based on user transaction data to deploying and monitoring production-ready ML models that drive critical product decisions.

To succeed, you’ll need a deep technical foundation in machine learning and statistical modeling, hands-on experience in model deployment, and strong communication skills to collaborate with engineers, product managers, and risk teams.

Key Responsibilities

• Develop and maintain credit risk and repayment models that directly power Clair’s underwriting and decision systems.
• Design and engineer predictive features using transaction-level data, including the prediction of user income flows, spending, and repayment behaviors.
• Collaborate with engineering teams to deploy, monitor, and optimize models in production environments using AWS and Snowflake ML Platform.
• Build prototypes of new modeling methodologies and present them to stakeholders for evaluation and feedback.
• Investigate and analyze credit performance, identifying root causes of model drift or unexpected repayment behavior.
• Partner cross-functionally with product, risk, and engineering teams to turn data insights into product improvements and credit strategy refinements.
• Communicate technical concepts clearly to both technical and non-technical audiences.
• Stay current on best practices and emerging techniques in credit modeling, explainable AI, and financial ML systems.
  

• 5+ years of professional experience in data science and machine learning.
• Proven track record of leading end-to-end data science projects — from research and model development to deployment and monitoring.
• Experience building and productionizing credit or risk assessment models.
• Strong proficiency in Python and familiarity with modern ML libraries (TensorFlow, PyTorch, XGBoost, etc.).
• Strong command of SQL and experience working with large transactional and time-series datasets.
• Strong communication skills and ability to translate complex findings into actionable insights.
• Experience working with cross-functional teams in a fast-paced production environment.

• Experience in fintech or credit risk modeling.
• Experience with cloud-based machine learning environments (AWS, Azure, Snowflake ML Platform, etc.).
• Familiarity with model explainability techniques and compliance requirements in financial modeling.
• Experience working with time-series analysis and modeling, including forecasting, trend detection, and temporal feature engineering

Additional Details

Location: This is a hybrid position based out in New York City, you will be expected to come into the office at least three days a week (Tuesdays, Wednesdays, & Thursdays) with additional days on occasion for client meetings.

Compensation: The annual base salary for this role is $165,000 to $172,000. The base pay for this role is determined using many factors, such as education, skills and experience and is reflective of Clair Series stage and size.  Base pay is only one part of Clair’s competitive total compensation package which includes equity, benefits and additional perks. The base pay range is subject to change and may be modified in the future.

Clair will only contact candidates from @getclair.com email addresses. We will never ask for payments or sensitive personal information during the hiring process. If you happen to receive anything suspicious, please ignore it.