Data Scientist

About the Company

Andela’s mission is to connect exceptional talent with meaningful opportunity. Since 2014, the company has focused on removing barriers to global work and enabling long-term growth for technologists and businesses worldwide. Team members gain access to strong career opportunities, a worldwide professional network, and learning opportunities through top technology partners. Andela is a remote-first organization and values an E.P.I.C. approach to building transformative, lasting growth.

Applicants who move forward will be asked to complete a technical screening and a live interview in order to join the Andela Community. Community members can access additional technologist opportunities across the global marketplace. Open roles tend to close quickly, so early applications are encouraged.

This position is a full-time contract role and compensation is paid in USD.

Role Summary

The Data Scientist will help shape the data intelligence foundation for an implementation programme. Working inside a cross-functional technology squad, this role focuses on deploying propensity models, creating customer segments, supporting PAN-based analytics, measuring digital lift, and building dashboards that inform acquisition, activation, and usage campaigns. The person in this role will coordinate with backend and API integration engineers to operationalize data pipelines, while also working with marketing and product teams to turn analytical findings into practical campaign decisions.

Key Responsibilities

This role involves creating a compliant PAN extraction and pseudonymization method for campaign analytics, while respecting data governance, PCI-DSS, and privacy requirements. It also includes building, testing, and launching propensity models to identify customers most likely to respond to digital payment acquisition, activation, and usage initiatives such as Visa card adoption, Visa Direct usage, and tokenization. In addition, the Data Scientist will create segmentation models that combine transactional, behavioral, and demographic data to form useful audience groups for marketing teams.

Other responsibilities include designing a digital lift measurement framework with control and treatment groups, attribution rules, and statistical significance thresholds; producing dashboards and reporting packs that clearly show campaign performance, model outputs, and digital adoption trends; and working with backend engineers to ensure data pipelines deliver fresh, accurate, and well-structured inputs for analysis. The role also requires close alignment with frontend engineering to validate event tracking and app instrumentation, plus analytical support for the diaspora consumer proposition workstream through remittance, activation, and channel preference analysis.

Additional duties include checking data quality across source systems, defining quality rules, escalating issues to engineering, documenting models and methods in reproducible notebooks and reports, transferring knowledge to internal analytics teams, and maintaining compliance with all data governance policies by raising concerns with the Scrum Master and relevant stakeholders when needed.

Measurable Outcomes

Within the first 30 days, the expected outputs include a completed assessment of the data landscape, a reviewed and documented PAN-handling governance approach, a defined propensity model scope with initial EDA, a first version of the digital lift framework reviewed with stakeholders, and shared analytics tracking requirements with the frontend engineer.

Between days 31 and 60, the role is expected to deliver a validated propensity model, the first customer cohort for campaign use, an operational feature-ingestion pipeline in development or staging, a baseline for digital lift measurement for at least one campaign, and a live analytics dashboard showing key KPIs.

Between days 61 and 90, expected outcomes include a production-ready scoring model and refresh cadence, at least one measured campaign cycle with statistically supported results, an operational PAN-based analytics approach within the approved governance framework, diaspora consumer analytics findings and recommendations, and complete documentation that enables the client data team to operate and retrain the model.

Required Experience and Technical Knowledge

The ideal candidate will bring at least 6 years of data science experience, including a minimum of 4 years in payments, fintech, financial services, or telecom. They should have hands-on experience taking propensity or classification models from development into production or near-production, along with a solid understanding of the full machine learning lifecycle from exploration and feature engineering through validation, deployment, and monitoring.

Strong capability in customer segmentation and campaign analytics is required, along with a clear understanding of PAN-based analytics and the governance, PCI-DSS, and privacy controls that must surround them. The role also calls for strong programming ability in Python and/or R, especially with pandas, scikit-learn, XGBoost or LightGBM, and statsmodels. Experience with A/B testing and causal inference for digital lift analysis is important, as is the ability to build and support data pipelines using SQL, dbt, Airflow, or similar tools. Candidates should also be able to produce polished dashboards and insight reports using tools such as Tableau, Power BI, or Looker, and should be comfortable setting data quality standards and communicating analytical results clearly to non-technical stakeholders.

Preferred Experience

Extra value will be given to candidates who have worked on mobile money or digital payment analytics such as M-Pesa or similar platforms, understand diaspora remittance behavior or cross-border payment patterns, have exposure to differential privacy or anonymization methods for payment data, have used MLOps tools such as MLflow, Vertex AI, or SageMaker, and have experience working in emerging market data environments with sparsity, network effects, or airtime-credit proxies.

Tools and Technologies

The role uses Python, SQL, dbt, Apache Airflow, Tableau, Power BI, Jupyter, Git, Azure, Confluence or SharePoint, and Jira or Azure DevOps as part of the day-to-day workflow.

Equal Opportunity Commitment

Andela is committed to maintaining a respectful and inclusive workplace. All employees and applicants are treated fairly and are protected from discrimination and harassment. Hiring, promotion, compensation, training, and all other employment decisions are made without regard to race, color, religion, gender, sexual orientation, gender identity, national origin, age, disability, pregnancy or breastfeeding status, genetic information, HIV/AIDS or other medical status, family or parental status, marital status, amnesty, or veteran status, in line with applicable laws and company policy.