Senior Data Scientist

Indsafri; South Africa; On-site; ZAR 1,000,000 - 1,800,000; Full time

Job summary

Indsafri is seeking a Senior Data Scientist to join the advanced analytics team in South Africa. You will lead end-to-end data solutions, applying machine learning, graph analytics, and GenAI to fraud detection and financial crime prevention.

Expertise in Python and cloud platforms is essential for production deployment. You will design predictive models, develop knowledge graphs, and guide data-driven decisions across enterprise datasets.

Qualifications

• Extensive experience with Python and core data science libraries.
• Hands-on graph analytics experience with graph databases or network analysis.
• Strong ML knowledge and production deployment expertise.

Responsibilities

• Model development: design, build, and deploy predictive models and analytics solutions.
• Graph analytics: implement knowledge graphs to reveal patterns in complex data.
• GenAI integration: leverage graphs to enhance model context and performance.
• Feature engineering: develop robust pipelines for model accuracy and efficiency.
• Lifecycle management: manage data prep, experimentation, and deployment.
• Technical leadership: drive best practices in code quality and scalability.

Skills

Python

Pandas

NumPy

Scikit-Learn

PyTorch/TensorFlow

Graph analytics

Neo4j

Knowledge graphs

AWS

GCP

Azure

MLOps

Tools

Docker

Kubernetes

CI/CD

Job description

We are seeking a highly skilled Senior Data Scientist to join our advanced analytics team. In this role, you will leverage machine learning, predictive modeling, and graph-based techniques to solve complex, high-impact business challenges, including fraud detection, financial crime prevention, and customer intelligence. You will be responsible for the end-to-end development of data solutions, specifically focusing on integrating knowledge graphs and GenAI capabilities to extract actionable insights from interconnected datasets. The ideal candidate is an expert in Python and cloud-native environments, capable of driving innovation from model conceptualization to production deployment.

Key Responsibilities

• Model Development: Design, build, and deploy predictive models and advanced analytics solutions to address critical enterprise use cases.
• Graph Analytics: Implement graph-based algorithms and knowledge graphs to uncover hidden patterns and relationships within complex data structures.
• GenAI Integration: Collaborate on AI/GenAI initiatives by leveraging knowledge graphs to enhance model performance and data context.
• Feature Engineering: Lead the development of robust feature engineering pipelines to improve the accuracy and efficiency of downstream machine learning models.
• Lifecycle Management: Manage the end-to-end model lifecycle, including data preparation, experimentation, performance optimization, and deployment within enterprise data environments.
• Technical Leadership: Drive best practices in code quality, model evaluation, and scalability across the data science team.

Required Skills and Qualifications

• Technical Proficiency: Extensive experience with Python and core data science libraries (e.g., Pandas, NumPy, Scikit-Learn, PyTorch/TensorFlow).
• Graph Expertise: Hands-on experience with graph analytics, graph databases (e.g., Neo4j, Amazon Neptune), or network analysis techniques.
• Machine Learning: Strong theoretical and practical knowledge of supervised/unsupervised learning, feature engineering, and model deployment strategies.
• Cloud Platforms: Proven experience working with cloud-native data environments (e.g., AWS, GCP, or Azure).
• Problem Solving: Demonstrated ability to translate complex business requirements into scalable, high-performance data solutions.

Preferred Qualifications

• Experience in the Financial Services domain (Fraud/Financial Crime focus).
• Familiarity with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks.
• Experience with containerization (Docker, Kubernetes) and CI/CD pipelines for MLOps.
• Track record of leading data science projects that have been successfully deployed into production environments.