Job Description
As a Data Scientist II at Klivvr, you'll own data science projects end to end, from framing the problem through shipping models that power our products and shape key business decisions. You'll partner closely with Product, Engineering, Marketing, and Risk to turn ambiguous, high-stakes problems into production-grade systems, and play a direct part in defining the future of fintech across the region.
This is a role for someone ready to operate with limited guidance: scoping their own work, making sound technical calls, and being accountable for the systems they build.
What you'll do:
- Own statistical and machine learning models for problems like customer segmentation, credit scoring, and fraud detection, from framing through deployment.
- Translate ambiguous business problems into well-scoped analytical solutions with measurable impact.
- Take models into production yourself in partnership with data engineers, and stay accountable for them once they're live.
- Dig into user behavior and transactional data to surface trends, patterns, and opportunities others miss.
- Communicate findings and recommendations clearly to both technical and non-technical audiences.
- Monitor model health after deployment and continuously improve performance over time.
- Contribute to our internal data science frameworks, tooling, and engineering best practices.
To succeed in this role, you'll need to have:
- 3+ years of hands-on data science or applied ML experience, including at least one model you took from problem framing through production.
- Strong proficiency in Python (NumPy, pandas, scikit-learn) and SQL.
- Solid grounding in statistics, probability, and core machine learning methods.
- Experience working with large-scale datasets on cloud platforms (AWS preferred).
- Sound engineering judgment and the ability to work independently within a collaborative team.
- Strong communication skills and a track record of working effectively across functions.
- Experience in fintech or consumer finance, especially with regulated problems like credit or fraud.
Nice to have:
- Familiarity with MLOps tooling such as MLflow and Docker.
- Experience with BI tools such as Looker or Tableau.
