Senior Data Scientist

Possible Finance builds data-driven strategies that improve how payments perform across real customer bank accounts. In this hybrid role in Seattle, WA, you will own analytical systems used to track payments health, monitor anomalies, optimize pay-cycle timing and retry behavior, and improve fraud risk understanding.

You will work in a team environment shaped by ownership, a scientific approach to experimentation, and intellectual honesty when the data points elsewhere. The work is mission-driven, with strategies that directly affect money movement and customer outcomes.

What you’ll do

• Own the data science behind how money moves at Possible.
• Define and build a payments-health scorecard that the company runs on.
• Build monitoring to surface anomalies at the channel and experiment level within days.
• Own how Possible times payments by sharpening how a customer’s pay cycle is identified and designing retry strategies aligned to that timing.
• Redefine how Possible understands payments fraud through recurring reporting on patterns that matter.
• Develop a model that scores the risk of a new payment method and the risk of a payment that may not clear.
• Use Python, SQL, and PySpark on Databricks, with Datadog for monitoring and standard MLOps tooling for deployment.
• Partner with Engineering, Product, and Risk to define the payment strategy as an input to the engineering roadmap.

What you bring

• Depth in data science fundamentals and payments domain knowledge.
• Experience with modeling, production monitoring, and experiment design.
• In-depth understanding of payment rails including ACH, RTP, card, and interchange, plus payment behavior.
• Hands-on production ML experience, including building a model, deploying it, monitoring drift, and retraining, using tools like XGBoost and MLflow (or equivalents).
• Strong Python and SQL.
• Comfort working with large datasets in distributed environments such as PySpark on Databricks.
• Experimentation and causal inference skills.
• Judgment to select the right method for each question.
• Feature engineering instincts for transactional data.
• A high bar for your own work: understand your data thoroughly and identify flaws in your analysis.
• Preferred: a track record of cross-functional collaboration that shaped another team’s roadmap.
• Preferred: hands-on experience with observability tooling such as Datadog.
• Nice-to-have: direct fraud modeling experience.
• Nice-to-have: background in collections, recovery, or lending operations in a regulated space.

Tools you’ll use

Python, SQL, PySpark, Databricks, Datadog, XGBoost, MLflow

Hybrid schedule

• Work in the office three days per week (Monday, Tuesday, Thursday).
• Office location: downtown Seattle.

Compensation and benefits

• Compensation range: $175,720 to $191,000 per year.
• Significant stock options
• Full benefits
• Bonus plan
• Commuter benefits
• Very desirable office with free drink and food options