Back to Jobs
Data Scientist - Credit Eligibility
M-KOPA · Remote · Full-time
Data & Analytics Easy Apply Remote
Apply Now
Posted 3 weeks ago · Job #37
About the Role

About This Opportunity

M-KOPA has redefined financial inclusion across Africa by combining smartphone and asset financing with sophisticated mobile credit, building a customer base of over 3 million people across Kenya, Uganda, Ghana, Nigeria, and South Africa. The company's model — enabling customers to pay for smartphones, solar systems, and other productive assets in small daily micro-payments — generates a rich, proprietary repayment dataset that fuels some of the most innovative credit scoring work happening anywhere on the continent.

This Data Scientist role sits at the core of M-KOPA's commercial strategy. The models you build will directly determine who receives credit, at what price, and under what risk parameters — decisions that simultaneously affect commercial performance and financial access for people at the base of the economic pyramid. This is high-stakes, high-impact data science in the truest sense of the phrase.

M-KOPA is backed by global investors including Sumitomo Corporation, Standard Bank, and the CDC Group, and has built one of the most technically sophisticated data science organisations in African fintech — making it an exceptional career environment for a specialist who wants both technical depth and social impact.


What You'll Do

At M-KOPA, you'll build and refine the predictive models that power our lending strategy. You'll sit within a small, high-performing team with end-to-end ownership of credit scoring, loan eligibility, and pricing optimisation — working cross-functionally with engineers, analysts, growth managers, and commercial stakeholders across multiple countries. Join us in combining cutting-edge data science with purpose-driven work that makes digital and financial inclusion possible across Africa.

Day to day, you'll be:

Building and refining credit scoring models that assess customer creditworthiness, default risk, and loan pricing across multiple markets

Developing and testing ML models for loan eligibility and pricing optimisation through A/B testing and statistical analysis

Continuously improving eligibility criteria by analysing repayment data, engineering new features, and monitoring credit performance for risk shifts and margin impact

Collaborating cross-functionally with engineers, data scientists, and commercial stakeholders to scale models into production

Technical Environment 💻

Languages & Libraries: Python, SQL, scikit-learn, pandas, numpy, and relevant ML libraries

Techniques: Predictive modelling, classification/regression, feature engineering, model selection, hyperparameter tuning, A/B testing

Domain: Credit scoring, underwriting, loan pricing, risk analytics

Our Team Approach

Low-ego environment where diversity, innovation, and collaboration drive both commercial growth and social impact

High degree of ownership over your domain — you're empowered to make data-driven decisions and prioritise solutions

Cross-functional collaboration with engineering, product, and commercial teams across multiple countries

Analytical rigour combined with deep market understanding to serve customers excluded from formal financial services


Applying for This Role

  • Build a portfolio before you apply: M-KOPA's selection process includes a technical assessment. Having end-to-end model development work — from exploratory data analysis through feature engineering to model evaluation — ready to discuss will make a significant difference.
  • Python, SQL, and scikit-learn are baseline requirements: These are not "nice to have." If any of these are weak, invest time strengthening them before applying.
  • A/B testing design is specifically valued: Prepare examples of experiments you have designed, the statistical methodology you used, and the commercial decision your results informed.
  • Demonstrate cross-functional communication: M-KOPA operates in a commercially driven environment. Show that you can translate model outputs into actionable business recommendations for non-technical stakeholders.
Requirements

Required Experience:

Experience building predictive models, particularly credit scoring, risk models, or similar classification/regression problems

ML background with hands-on experience in model development, validation, deployment, and performance monitoring

Proficiency in Python, SQL, and relevant ML libraries (scikit-learn, pandas, numpy, etc.) with experience in feature engineering, model selection, and hyperparameter tuning

Experience translating complex model outputs into actionable business strategies and stakeholder communications

Ability to work cross-functionally with product, engineering, and commercial teams

Strong data communication skills — written, oral, and visual

Highly Desirable:

Experience in credit, underwriting, lending analytics, or fintech modelling

Benefits

Location & Benefits

Fully remote role within UTC -1 to UTC +3 time zones

Work with diverse teams across UK, Europe, and Africa

Professional development programmes and coaching partnerships

Family-friendly policies and flexible working arrangements

Well-being support and career growth opportunities

About M-KOPA
M-KOPA
Fintech & Clean Energy · 1,001–5,000 employees

M-KOPA is a connected asset financing platform that delivers affordable solar energy, smartphones, and digital financial services to underserved consumers across sub-Saharan Africa. By combining IoT technology with flexible pay-as-you-go financing, M-KOPA has transformed the lives of over three million customers who previously lacked access to formal credit or reliable energy.

🧭
Application Guide for This Role
Tailored tips to help you stand out and prepare confidently
📊 What Data & Analytics Hiring Managers Look For

Data teams want analysts who can formulate the right question before touching a query. Technical fluency (SQL, Python, visualisation tools) is the baseline — the real differentiator is whether you can translate findings into decisions that non-technical stakeholders will act on.

How to Stand Out
  • Showcase a project where your analysis directly influenced a product or business decision — not just a dashboard.
  • Demonstrate SQL proficiency with window functions, CTEs, and performance optimisation if the role involves large datasets.
  • Mention experience with A/B testing methodology, statistical significance, and experiment design.
  • Show comfort with ambiguity: describe a time you defined a metric from scratch when no standard existed.
Likely Interview Questions
  1. You're given a dataset with a 15% drop in a key metric — walk me through how you'd investigate the cause.
  2. How do you decide which metrics to track for a new feature?
  3. Describe a time your analysis was wrong — how did you catch it, and what was the impact?
  4. How do you build trust with stakeholders who are sceptical of data?
Pro tip: Practice explaining a SQL query or statistical concept to a non-technical person — this skill is tested more often than raw query writing in interviews.
📄 About Full-Time Employment Roles

Full-time roles typically include benefits (health insurance, pension contributions, paid leave). During salary negotiation, always consider the total compensation package — benefits can be worth 20–30% on top of base salary. Ask specifically about probation period, performance review cadence, and remote/hybrid flexibility before signing.

🏠 Remote Work — What to Expect

Remote roles give you location freedom but require strong self-management. Before accepting, confirm: What are the core overlap hours? Which collaboration tools does the team use (Slack, Notion, Linear, Figma)? Is there a home-office stipend? How does the team handle onboarding for remote hires? Remote-first companies typically have better async culture than companies that went remote reluctantly — ask how decisions get documented.

✅ Before You Hit Submit
📝
Tailor your CV
Remove irrelevant roles. Match your language to the job description — ATS systems score keyword alignment.
💌
Write a real cover note
One paragraph that explains why this specific company, this specific role, right now. Generic notes go unread.
🔍
Research the company
Know their product, recent news, funding stage, and competitors. Bring one insight to your interview.
🔗
Clean up your LinkedIn
Make sure your profile matches your CV and your headline reflects the role you want, not the one you are leaving.
Job Overview
Salary Competitive
Type Full-time
Location Remote
Category Data & Analytics
Posted Apr 27, 2026
Apply Now
Free Daily Digest
Stay ahead of the job market

New jobs, scholarships and career tips — delivered to your inbox daily. Unsubscribe any time.