Principal Data Scientist
New York, NY /
SeedFi is a mission-driven startup dedicated to improving the financial well-being of the 100 million Americans who live paycheck to paycheck. Our mission is to help our customers realize their financial potential by providing responsible credit while helping them establish savings and improve their credit profiles.
Unlike most startups in this space, which tweak existing products, we're re-imagining financial services from the ground up. Our goal is to leave our customers better off than when we found them.
About the role
As a principal data scientist on the risk team, you’ll help identify value in our data to drive down credit risk and support other modeling use cases. You will collaborate with others on the data science team to incorporate that signal into data features, develop and continuously improve our machine learning solutions and support the growing list of products and services SeedFi offers its customers. The ideal candidate is excited to uncover signals in the data, develop data features and machine learning models that allow us to confidently predict customer risk, and to be a part of an early stage data science team on a mission to improve access to credit.
What you'll be doing
- Analyze internal and external data including credit bureau, bank account, and other alternative data to uncover new risk insights.
- Collaborate with key stakeholders to understand business problems, ideate ML solutions and effectively communicate to stakeholders.
- Research, develop and apply ML/AI solutions to solve business problems, including prediction, optimization, and segmentation.
- Conduct model related analyses to provide comprehensive insights about ML solutions.
What we're looking for
- Desire to improve financial health for struggling Americans and make a real difference in people’s lives.
- 3+ years of hands-on experience developing consumer credit risk models at a FinTech company.
- Previous experience in extracting risk signals from bank account data is a plus.
- Deep knowledge of machine learning modeling.
- Proficient in both Python (and the library ecosystems used for data cleaning, analysis, visualization, feature engineering, model creation and model evaluation, such as pandas, sci-kit learn, matplotlib, etc.) and SQL.
- Some formal academic training in machine learning (preferably an MS degree).
- A deep sense of intellectual curiosity with a focus on results, as you continue to identify value in our data across modeling use cases.
- Competitive compensation, equity, and benefits.
- A focus on transparency. We have regular all-hands and Q&A panels where employees can chat openly with our co-founders about our roadmap.
- Meaningful work that makes people's lives better.
- An inclusive and collaborative work environment that encourages agency and self-development.
- Our founding team has deep experience building and scaling fintech (and tech) companies from inception to profitable 1,000+ person businesses. Some of the companies we have helped build are: CapOne, Marcus, BlueVine, Oportun, and Prosper.
- Our engineering team comes from Moat, Bloomberg, ZocDoc, CreditKarma, Chime, and other great companies.
- We've raised $34 million of venture capital from some of Silicon Valley’s top venture capital and social impact funds including a16z, Flourish, and Core Innovation Capital.
We have offices in San Francisco and New York. We have started to reintegrate in-office time into our working routines with a long-term vision of creating a hybrid working environment that mixes in-office and remote time. Our goal is to utilize in-office time to effectively collaborate on complex projects and problems, build relationships across the organization, and engage in social activities. We also want to embrace the efficiency and effectiveness we have experienced over the last year and a half in getting individual contributor work done remotely. Specific working routines may vary depending on your role.