Senior Quantitative Analyst

Job Requisition Details

REQ#142178

Location: Johannesburg, Gauteng

Closing Date: 24 February 2026

Talent Acquisition: Bongiwe Mchunu

Job Family

Career Stream

Leadership Pipeline

FAIS Affected

Job Purpose

To design, build, and maintain the core data infrastructure that powers Nedbank’s modern credit and customer analytics ecosystem. The role is responsible for developing scalable data pipelines, architecting and operationalising reusable feature stores, and implementing robust metadata and data governance frameworks.

The incumbent will ensure that high‑quality, well‑documented, production‑ready data is consistently available for modelling teams, real‑time systems, and downstream analytics. This role provides the foundational data engineering capability that enables model developers, MLOps engineers, and analytics teams to deliver models faster, safer, and with higher predictive integrity.

The incumbent drives the standardisation of data patterns, reusable assets, and governed feature frameworks, which materially reduce model cycle time and operational risk.

Job Responsibilities

• Design, build, and optimise large‑scale data pipelines using Python, Spark, and distributed compute frameworks to support high‑throughput modelling and analytics workloads.
• Architect, implement, and maintain the enterprise feature store, ensuring consistency, versioning, reusability, and governance across modelling teams and real‑time scoring environments.
• Establish and maintain metadata management frameworks, covering data lineage, data contracts, schema evolution, feature definitions, and end‑to‑end traceability.
• Develop automated data ingestion and transformation workflows, ensuring repeatability, performance optimisation, and alignment with modern engineering practices.
• Implement data quality monitoring, validation rules, and observability tooling (e.g., schema checks, drift detection, pipeline health metrics) to ensure reliable, production‑grade data.
• Collaborate with model developers, MLOps engineers, and platform teams to enable seamless model training, deployment, and monitoring via well‑engineered data foundations.
• Contribute to the design and evolution of the modern modelling ecosystem, including feature store architecture, metadata strategy, and standardised data patterns.
• Ensure data governance and compliance through documentation, automated controls, and integration with internal regulatory and risk frameworks.
• Drive automation and simplification across data preparation processes to reduce modelling cycle times and improve platform scalability.
• Conduct performance tuning and optimisation of Spark pipelines, storage formats, and distributed compute resources.
• Participate in code reviews, design discussions, and engineering best‑practice forums, promoting clean, modular, and maintainable data engineering standards.
• Support junior team members through mentoring, technical guidance, and knowledge sharing, contributing to uplift across the broader modelling community.
• Conduct horizon scanning on emerging data engineering, metadata, and feature store technologies.
• Prototype new data frameworks, storage formats, and distributed processing techniques.

Professional Exposure

The ideal candidate will have practical, hands-on exposure to:

• Software Engineering / Coding Fundamentals: Solid grounding in computer science/coding principles, including Object-Oriented Programming (OOP), design patterns, data structures, and algorithmic complexity (Big-O).
• Distributed Computing & Big Data: Working with large-scale data processing systems and distributed environments.
• Modern DevOps Integration: Active usage of CI/CD pipelines, version control (Git), and containerisation technologies (Docker/Kubernetes) within a microservices or API-driven architecture.
• Deep Learning & Optimisation: Proficiency with ML frameworks (e.g., TensorFlow, PyTorch, Scikit-learn) and application of continuous/discrete mathematical optimisation techniques.
• Model Governance: Productionising models with rigorous tracking, specific versioning, and governance using tools such as MLFlow.

Professional Knowledge

Core Programming & Engineering

• Expert Proficiency: Advanced Python skills with deep knowledge of ML ecosystems (TensorFlow, PyTorch, Scikit-learn).
• Computer Science Fundamentals: Mastery of Object-Oriented Programming (OOP) patterns, data structures, algorithms, and complexity analysis (Big-O).
• Polyglot Advantage: Exposure to performance-aligned languages such as Java, C++, Go, or Rust is advantageous (though not required).

Data, MLOps & Infrastructure

• Big Data Ecosystems: Strong command of distributed data systems (SQL, Spark) and cloud-native data tooling.
• MLOps Architecture: Practical knowledge of model lifecycle management (MLFlow), containerisation (Docker/Kubernetes), CI/CD pipelines, and API integration.
• Data Strategy: Expertise in designing feature stores, high-performance feature engineering, and managing the end-to-end data lifecycle.

Mathematical & Domain Expertise

• Theoretical Depth: Solid grasp of vector calculus, linear algebra, probability theory, statistical inference, and mathematical optimisation.
• Governance & Risk: Understanding of model governance, regulatory modelling standards, and frameworks specific to credit or risk modelling.

Behavioural Competencies

• Innovative & Curious: A relentless learner who stays ahead of the curve, passionate about applying emerging technologies and modern analytical approaches to solve old problems.
• Analytical Problem Solver: Possesses the intellect to deconstruct complex, ambiguous modelling challenges into scalable, logical solutions.
• Collaborative Powerhouse: A cross-functional partner who drives impact through strong stakeholder management, capable of delivering results individually or by influencing others.
• Resilient & Adaptable: Thrives in rapidly evolving environments; comfortable with ambiguity and quick to pivot strategies when business needs change.
• Technical Communicator: Translates dense technical concepts into clear, actionable insights for non-technical leadership.
• Owner's Mindset: Takes full accountability for the end-to-end delivery and reliability of modelling solutions.
• Force Multiplier: Demonstrates a coaching mindset, actively mentoring junior analysts to uplift the team's overall technical capability.

Essential Qualifications - NQF Level

Qualification

Minimum Requirements

• Honours Degree in a quantitative or technical discipline, like Computer Science, Engineering (Industrial, Electrical, Computer), Mathematics/Applied Mathematics, Statistics, or Computational/Theoretical Physics.

Preferred

• Master’s Degree (or higher) in a related quantitative field

Minimum Experience Level

• 5-8 years of core experience in quantitative modelling, data science, or advanced analytics.
• Production Engineering: Demonstrated ability to write robust, modular, and well-structured Python code for production environments.
• Domain Expertise: Proven track record in building and deploying machine learning models, with specific experience in Credit Risk or financial modelling being highly advantageous.
• Agile Delivery: Experience working within Agile data science or engineering squads.

Technical / Professional Knowledge

Behavioural Competencies