SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 175,720 - 191,000 / annual
Possible is a mission-driven fintech company helping everyday Americans build financial health through access to fair, affordable credit. The data team sits at the center of the company, building models, metrics, and experimentation infrastructure that powers decision-making, performance measurement, and rigorous operations at scale.
You will own the data science behind how money moves at Possible. Your responsibilities include:
- Define and build the payments-health scorecard that governs company operations, along with monitoring systems that surface anomalies at the channel and experiment level within days.
- Own payment timing strategy: sharpen identification of customer pay cycles and design retry strategies that work with customer financial rhythms, reducing failed-payment fees and improving recovery.
- Redefine how Possible understands payments fraud: build recurring reporting on relevant patterns and develop models that score the risk of new payment methods or payments that may not clear.
- Partner with Engineering, Product, and Risk to develop payment strategy as input to the engineering roadmap.
You will work in Python, SQL, and PySpark on Databricks, with Datadog for monitoring and standard MLOps tooling for deployment. This role emphasizes ownership—you'll define what healthy payments means rather than waiting for specifications. The company takes a scientific approach: rapid experimentation, intellectual honesty, and willingness to change direction based on data. The work is mission-driven in concrete ways, as your strategies directly impact real customers' bank accounts and financial outcomes.
Possible Finance is a venture-backed Public Benefit Corporation backed by Union Square Ventures, Canvas Ventures, Euclidean Capital, and Unlock Venture Partners. The company has hundreds of thousands of loyal customers and is committed to breaking the debt cycle and unlocking economic mobility.
Hybrid position: three days per week in downtown Seattle office (Monday, Tuesday, Thursday).
REQUIREMENTS
Must-Have:
- Depth in data science fundamentals and payments domain knowledge
- Experience with modeling, production monitoring, and experiment design
- In-depth understanding of payment rails (ACH, RTP, card, interchange) and payment behavior
- Hands-on production ML development: built, deployed, monitored drift, and retrained models using tools like XGBoost and MLflow or equivalents
- Strong Python and SQL skills
- Comfort with large datasets in distributed environments (PySpark on Databricks)
- Experimentation and causal inference skills with judgment to select appropriate methods
- Feature engineering instincts for transactional data
- High standards for own work: understand data before drawing conclusions; identify flaws in own analysis
Preferred:
- Track record of cross-functional collaboration that shaped another team's roadmap (not just informed it)
- Hands-on experience with observability tooling such as Datadog
Nice-to-Have:
- Direct fraud modeling experience
- Background in collections, recovery, or lending operations in regulated space
