Senior Data Scientist - Credit Underwriting

About the Role

We are looking for an experienced Senior Data Scientist to join our team, focusing on credit underwriting within the embedded fintech space. You'll be responsible for developing critical components of Clair's loan underwriting engine. The methodologies you develop and apply will directly shape how millions of hourly workers unlock an untapped credit source: their earned wages. In this role, you'll shape our credit strategies, develop innovative predictive models, and ensure compliance with regulatory guidelines. You'll work on high-stakes initiatives like predictive employment tenure and termination models based on employee tenure, shift behavior, pay history, title, industry, and other factors.

To succeed in this role, you'll need a deep technical understanding of data science concepts and machine learning. You'll also need to be comfortable building prototypes of novel methodologies from scratch and deploying models to a production environment. Strong business acumen and a track record of data-driven decision-making are essential. You should also have deep knowledge and experience with financial technology and modeling, particularly underwriting, credit risk scoring, and repayment timing optimization.

Key Responsibilities

• Create new algorithms and predictive models to assess risk and underwrite loans.
• Collaborate with engineering teams to deploy models to a production environment.
• Communicate about algorithms and their business value to technical and non-technical audiences.
• Build supervised and unsupervised learning systems to glean insight from our wide variety of data sources.
• Lead cross-discipline projects fostering collaboration between product, software engineering, data engineering, and data science teams.
• Investigate root causes of credit loss-related issues through exploratory data analysis and domain research
• Create prototypes to expose algorithms to stakeholders for gathering research feedback.
• Design research frameworks to capture and evaluate results.
• Monitor and validate the performance of credit models post-launch, iterating as needed to optimize outcomes.
• Stay current on regulatory changes and industry best practices in credit risk and financial modeling.

Qualifications

• 5+ years of work or educational experience in data science and machine learning.
• Proven leadership of data science projects from conception to delivery.
• Proven track record of delivering on products and/or practical research endeavors.
• Experience in risk assessment and predictive modeling
• Experience in productionizing machine learning models, including the full pipeline from training to deployment as APIs.
• Experience with large transaction-based datasets.
• Experience with Python is required.
• Experience with Snowflake or similar data warehouse systems is a plus.
• Experience with AWS SageMaker, Lambda, Step Functions and other AWS tooling is a plus.
• Experience with a range of open-source and commercially available LLMs is a plus.
• Experience with spaCy, NLTK, or HuggingFace libraries is a plus.
• Experience with Tensorflow, Torch, Keras or similar libraries is a plus.

Additional Details

Location: This is a hybrid position based out of 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.