Applied Machine Learning Engineer - SDE 2

We are looking for a highly skilled Applied Machine Learning Engineer who combines strong mathematical foundations, software engineering excellence, and expertise in building scalable analytical systems. This role is not focused on ad hoc analytics, notebook-based experimentation, or model development in isolation. We are seeking engineers who can design, develop, operationalise, and scale statistical and machine learning solutions that solve complex business problems in production environments. You will work at the intersection of software engineering, machine learning, forecasting, optimisation, and big data technologies. Success in this role requires a deep understanding of mathematics, statistics, machine learning, and forecasting methodologies, along with the engineering discipline required to transform analytical prototypes into reliable, maintainable, and scalable production systems.

We are particularly interested in candidates with experience supporting forecasting, planning, optimisation, or decision intelligence platforms in Supply Chain, Retail, Logistics, Manufacturing, or related domains. The ideal candidate is equally comfortable discussing statistical assumptions, forecasting accuracy, optimisation constraints, software architecture, distributed processing, feature engineering, and production reliability.

The candidate will have responsibilities across the following functions:

Statistical Modelling and Machine Learning:

• Design, develop, and improve statistical and machine learning models for forecasting, planning, optimisation, and decision-support solutions.
• Apply both classical statistical techniques and modern machine learning approaches to solve business problems.
• Select appropriate modelling methodologies based on business requirements, data characteristics, and operational constraints.
• Evaluate model performance using rigorous statistical, operational, and business metrics.
• Develop robust approaches for uncertainty estimation, model validation, and performance measurement.
• Continuously improve model quality, stability, scalability, and business impact.

Forecasting and Optimisation Solutions.

• Build forecasting solutions for demand planning, inventory management, replenishment, capacity planning, pricing, and operational decision-making.
• Develop probabilistic forecasting solutions where uncertainty estimation is critical.
• Design and implement optimisation models that support operational decision-making at scale.
• Balance model accuracy, interpretability, scalability, and operational usability.

Production Machine Learning Engineering:

• Partner closely with Data Scientists, Applied Scientists, Product Teams, and business stakeholders to translate analytical prototypes into production-grade solutions.
• Collaborate on model design, feature engineering, validation methodologies, and performance optimisation.
• Convert research-oriented or notebook-based implementations into scalable, reusable, and maintainable software systems.
• Design and implement reusable training, evaluation, inference, and retraining frameworks.
• Drive engineering best practices for productionizing statistical, forecasting, optimisation, and machine learning solutions.
• Establish standards that improve reproducibility, reliability, and maintainability of analytical systems.

Machine Learning Lifecycle Management:

• Build and maintain end-to-end machine learning workflows across training, validation, deployment, monitoring, and retraining stages.
• Implement robust model evaluation and validation processes.
• Develop model monitoring solutions that identify performance degradation, drift, and operational issues.
• Support experiment tracking, model versioning, and feature versioning.
• Leverage and contribute to ML lifecycle platforms and tooling, including MLflow, Feature Stores, model evaluation frameworks, and model monitoring solutions.
• Partner with platform and data engineering teams to improve ML platform capabilities and developer productivity.

Machine Learning at Scale:

• Design and build solutions capable of training and scoring models against large-scale datasets.
• Optimise feature engineering, model training, and inference workflows within distributed environments.
• Build scalable architectures that support millions of predictions and large volumes of operational data.
• Improve computational efficiency and cost-effectiveness of machine learning workloads.
• Balance modelling sophistication with operational and performance constraints.
• Operate comfortably within modern big data ecosystems and distributed computing environments.

Software Engineering Excellence:

• Design and develop production-quality software using modern engineering practices.
• Build reusable frameworks, SDKs, libraries, and shared components that support multiple modelling use cases.
• Apply object-oriented design principles and architectural patterns to analytical systems.
• Implement comprehensive testing strategies for model and application code.
• Continuously improve maintainability, reliability, and extensibility of solutions.

Requirements:

• Bachelor's or Master's degree in Computer Science, Statistics, Mathematics, Engineering, Operations Research, Economics, or a related discipline.
• 6+ years of experience developing statistical, forecasting, optimisation, or machine learning solutions in production environments.
• Strong programming skills in Python with the ability to write clean, maintainable, and testable code.
• Strong foundation in Object-Oriented Analysis and Design (OOAD).
• Experience designing and building production-grade software systems.
• Strong understanding of software architecture and system design fundamentals.

Mathematical and Statistical Foundations:

Strong foundation in:

• Mathematics
• Statistics
• Probability Theory
• Machine Learning
• Forecasting
• Optimization Techniques

Deep understanding of:

• Statistical Inference
• Hypothesis Testing
• Probability Distributions
• Time-Series Analysis
• Forecast Error Measurement
• Uncertainty Quantification

Strong understanding of:

• Feature Engineering
• Bias-Variance Tradeoffs
• Regularization Techniques
• Ensemble Methods
• Experimental Design
• Model Evaluation Methodologies
• Ability to reason about model assumptions, limitations, interpretability, and business applicability.

Machine Learning Engineering:

• Experience producing statistical and machine learning models.
• Experience partnering closely with Data Scientists to operationalise analytical solutions.
• Strong understanding of the end-to-end machine learning lifecycle.
• Experience designing scalable training, inference, and model evaluation workflows.
• Ability to translate mathematical models into maintainable software systems.

Big Data and Distributed Computing:

• Experience developing and scaling analytical workloads in distributed environments.
• Experience working within modern big data ecosystems.
• Hands-on experience with PySpark.
• Strong understanding of distributed data processing concepts and computational tradeoffs.
• Ability to design solutions that balance model accuracy, scalability, and computational efficiency.

Software Engineering Practices

• Strong understanding of:
• SOLID Principles
• Separation of Concerns
• Dependency Injection
• Encapsulation and Abstraction
• Composition over Inheritance
• Experience applying design patterns and architectural patterns appropriately.

Experience with:

• Code Reviews
• Unit Testing
• Integration Testing
• Test Automation
• CI/CD
• Version Control
• Refactoring and Technical Debt Management
• Passion for clean code, engineering craftsmanship, and long-term maintainability.

Preferred Qualifications:

• Supply Chain and Planning Domain Experience.
• Experience in Supply Chain, Retail, Manufacturing, Logistics, Planning Systems, or Operations platforms.

Experience developing solutions for:

• Demand Forecasting
• Inventory Optimization
• Replenishment Planning
• Supply Chain Planning
• Pricing and Promotion Analytics
• Capacity Planning
• Network Optimization

Forecasting and Statistical Modelling:

Experience with:

• SARIMAX
• Exponential Smoothing
• State Space Models
• Prophet
• Hierarchical Forecasting
• Intermittent Demand Forecasting
• Bayesian Forecasting
• Probabilistic Forecasting

Machine Learning and Advanced Analytics:

Experience with:

• ML algorithms
• Scikit-Learn
• Ensemble Methods
• Deep Learning
• Temporal Neural Networks
• Large-Scale Feature Engineering
• Explainability and Model Interpretability Techniques

Optimisation and Decision Science:

Experience with:

• Linear Programming
• Mixed Integer Programming
• Constraint Optimization
• Heuristic Optimization
• Network Optimization
• Simulation Modeling
• Operations Research Techniques

ML Platform and Lifecycle Management:

Hands-on experience with:

• MLflow
• Feature Stores
• Model Evaluation Frameworks
• Experiment Tracking Platforms
• Model Monitoring Solutions

Experience implementing:

• Model Versioning
• Feature Versioning
• Automated Model Validation
• Drift Detection
• Model Performance Monitoring

Platform and Engineering:

• Experience with Docker and Kubernetes.
• Experience building reusable frameworks, SDKs, or shared platform capabilities.
• Experience defining engineering standards and architectural best practices.
• Familiarity with Domain-Driven Design (DDD).
• Experience working closely with Data Engineering teams to deploy analytical solutions in large-scale data ecosystems.

What We Value

We value engineers who:

• Possess strong mathematical intuition and analytical rigour.
• Understand the assumptions behind models, not just the tools used to train them.
• Can explain why a model works and when it should not be used.
• Bridge the gap between Data Science and Software Engineering.
• Transform prototypes into scalable and maintainable production systems.
• Build reusable modelling frameworks rather than project-specific implementations.
• Apply OOAD principles, SOLID principles, and design patterns effectively.
• Write clean, readable, and maintainable code.
• Think beyond experimentation and focus on delivering business outcomes.
• Balance model accuracy, operational complexity, scalability, and cost.
• Take ownership of production systems throughout their lifecycle.
• Continuously improve architecture, engineering practices, and model reliability.

Skills

Azure AD, Azure PIM, Microsoft Entra ID, Privileged Identity Management