Data Science Engineer, Credit Scoring, ML & Advanced Analytics, Assistant Senior Manager at Diamond Trust Bank (DTB)

Job Purpose:

Lead the design and deployment of cutting‑edge machine learning and statistical models that power the bank’s most critical decisions across credit, fraud, customer management, marketing, and operations. Champion innovation within DTB’s risk and analytics ecosystem—driving advancements in credit scoring, alternative data modelling, forecasting, and real‑time decisioning. Your work will strengthen model accuracy, uphold regulatory compliance, and deliver measurable business impact, positioning data and AI at the heart of DTB’s digital evolution.

Key Responsibilities:

Credit-Risk & Lending Analytics (Primary)

• Lead development of credit-risk models:
  • Application & behaviour scorecards
  • PD/LGD/EAD models (Basel & IFRS9)
  • Credit limit assignment & pricing models
  • Champion–challenger frameworks
  • Build decision engines and real-time scoring capabilities.
• Oversee model monitoring, backtesting, calibration, and governance.

Customer & Product Analytics

• Develop customer lifetime value (CLV) models, churn prediction, segmentation models, and recommendation systems.
• Support pricing optimization for lending & deposits.
• Build models for product cross-sell, upsell, and next-best-action (NBA).

Fraud & Financial Crime ML

• Develop anomaly-detection, fraud detection, and real-time transaction scoring models.
• Implement behavioural biometrics and device-risk models.
• Work closely with Financial Crime & Cybersecurity teams to operationalize models.

Marketing, Personalization & CVM Analytics

• Build targeting models, propensity models, campaign uplift models, and customer segmentation.
• Partner with CVM team to automate customer journeys with ML-driven triggers.

Operational & Forecasting Models

• Forecast loan demand, deposits, NPL trajectories, collections performance, and cash flows.
• Work with Finance on balance-sheet forecasting and stress-testing scenarios.

NLP, Generative AI & Automation

• Develop NLP models for call-centre transcripts, customer messages, chatbots, and complaint classification.
• Implement GenAI for document classification, summarization, and knowledge discovery.
• Guide safe AI adoption, model governance, and prompt engineering.

Data Engineering & Big Data

• Build scalable pipelines using Spark, Hadoop, Kafka, Airflow.
• Collaborate with data engineering on feature stores, ML pipelines, and model CI/CD.

Leadership & Governance

• Mentor data scientists and analysts.
• Lead model governance sessions with Internal Audit, Model Risk, and Regulators.
• Translate complex models into actionable strategies for business leaders.

Qualifications & Experience:

• Advanced academic strength — a master’s degree in Statistics, Machine Learning, Data Science, Applied Mathematics, or Computer Science is highly preferred, showcasing your depth in analytical and quantitative disciplines.
• Proven leadership in data science — 7–12+ years of hands‑on experience building advanced models, including 5+ years specifically in banking credit risk, credit scoring, or regulatory modelling.
• Technical excellence — mastery of Python, SQL, Spark, and modern MLOps tools such as MLflow and Docker, with demonstrated experience implementing machine‑learning solutions at big‑data scale.
• Regulatory and risk expertise — strong, practical knowledge of IFRS9, Basel standards, and CBK model governance requirements, enabling you to build models that are both high‑performing and fully compliant.

Key Competencies

• Expertise that blends deep risk‑modelling mastery with versatile, modern machine‑learning skills, enabling you to build robust, scalable, and intelligent decisioning systems.
• Exceptional communication and storytelling ability, with the confidence to engage C‑suite leaders, influence strategic direction, and clearly articulate model insights to regulators.
• A strong strategic mindset, ensuring every model, feature, and analytical framework directly supports the bank’s business priorities, customer needs, and risk appetite