Data Science Engineer, Assistant Senior Manager at Diamond Trust Bank (DTB)

• Build and maintain ETL/ELT pipelines that feed modelling datasets from multiple banking systems (CBS, LMS, CRM, Cards, Mobile Banking, Bureau, Collections systems).
• Develop automated data preparation workflows for credit scoring, fraud models, behavioral models, and IFRS9 modelling.
• Create end-to-end ML pipelines integrating feature engineering, data validation, model deployment, and monitoring.
• Manage and Build other Enterprise ETL using tools like ODI , informatica etc.

• Develop scalable data-processing workflows using Spark, Hadoop, Kafka, Airflow, Flink or similar.
• Optimize large datasets (transactional, bureau, behavioural, logs) for modelling in batch and real-time environments.
• Manage distributed computation and ensure reliability and fault tolerance.

• Design and maintain a centralized feature store for credit, fraud, marketing, and customer analytics models.
• Ensure feature consistency between training and serving environments.
• Implement versioning, lineage, documentation, and metadata management for data features.

• Collaborate with data scientists to deploy models using MLflow, Docker, Kubernetes, API gateways, CI/CD pipelines.
• Develop automated monitoring pipelines for model performance, drift detection, data quality, and explainability.
• Ensure models operate efficiently in real-time decision engines and batch scoring environments.

• Implement robust data validation, profiling, anomaly detection, and reconciliation checks.
• Work with Data Governance teams to ensure compliance with IFRS9, Basel, CBK, GDPR, and internal data standards.
• Manage data lineage, cataloguing, and documentation to support audits and regulatory reviews.

• Partner with Data Scientists, Risk, Credit, Fraud, Marketing, and BI teams to align data pipelines with business use cases.
• Work with IT and Infrastructure teams on cluster performance, security, access controls, and SLA adherence.
• Participate in sprint planning, architecture reviews, and model implementation committee sessions.

• Improve the efficiency, scalability, and cost of ML workloads.
• Optimize database queries, Spark jobs, Kafka streams, and storage systems.

• Strong academic foundation with a Bachelor's or Master's in Computer Science, Data Engineering, Data Science, Information Technology, or a related quantitative field.
• 3-7+ years of impactful, hands-on experience in data engineering, big-data processing, or building scalable ML infrastructure-ideally within fast-paced, data-driven environments.
• Advanced programming capability, with strong proficiency in Python, SQL, and PySpark; experience with Scala is an added advantage.
• Demonstrated expertise in modern data and ML platforms, including:

• Big-data technologies: Spark, Hadoop, Kafka, Airflow
• MLOps & containerization: MLflow, Docker, Kubernetes
• CI/CD pipelines: GitLab, Jenkins, GitHub Actions
• Cloud platforms: AWS, GCP, or Azure (highly preferred)
• Experience working with banking systems, risk data, or credit-modelling datasets-a significant advantage that accelerates success in this role.

• Strong understanding of data structures, distributed systems, and ML workflows.
• Excellent problem-solving, debugging, and optimization skills.
• Fast learner with ability to adapt to new technologies.
• High attention to detail, documentation discipline, and data governance awareness.
• Strong collaboration and communication skills.

Jobs in Kenya