Job Summary

Data Scientist / Machine Learning Engineer (Predictive Analytics)

About the Role

We are seeking a versatile Data Scientist / Machine Learning Engineer to drive high-impact predictive analytics solutions. You will focus on diverse operational challenges, ranging from predictive asset maintenance to dynamic workforce optimisation and demand forecasting. You will leverage the Databricks platform on AWS to build, scale, and deploy robust ML models that integrate seamlessly with our clients' enterprise architectures (SAP, FSM, GIS, SCADA systems).

Key Responsibilities

Key Responsibilities

• End-to-End Predictive Modelling: Design and develop advanced predictive models to solve complex business problems, such as forecasting daily/hourly reactive workloads, predicting asset failures, and optimising resource allocation.
• Databricks Ecosystem Mastery: Utilise Databricks (Unity Catalog, Delta Lake, MLflow) to ingest, process, and analyse large-scale structured and unstructured data from diverse sources (e.g., SAP Datasphere, S3).
• Algorithm Versatility: Apply a wide range of ML techniques, including time-series forecasting (e.g., Prophet, XGBoost, LSTMs), statistical modelling, Bayesian Modelling and optimization algorithms (e.g., Operations Research, Linear Programming) based on the specific use case.
• Scenario Simulation: Build models that allow business users to simulate various operational scenarios (e.g., tweaking risk appetites, reallocating shifts) and evaluate projected outcomes.
• Cross-Functional Collaboration: Work alongside Data Engineers, Gen AI Experts (AWS Bedrock), and UI Developers to build "Compound AI" systems that combine predictive insights with generative AI explanations and user-friendly interfaces.

Skill Requirements

Required Skills & Qualifications

• Experience: Proven track record as a Data Scientist/ML Engineer delivering predictive models into production environments, ideally for operational, supply chain, or critical infrastructure use cases.
• Programming: Expert-level Python programming (pandas, scikit-learn, statsmodels, PyTorch/TensorFlow).
• Platform Expertise: Deep, hands-on experience with Databricks and the AWS cloud ecosystem.
• Mathematical Foundation: Strong understanding of probability, time-series analysis, and constrained optimization problems.
• Problem Solving: Ability to translate ambiguous business into structured mathematical frameworks.
• Experience in Energy & Utilities industry is a definite advantage.

Other Requirements

Required Skills & Qualifications

• Experience: Proven track record as a Data Scientist/ML Engineer delivering predictive models into production environments, ideally for operational, supply chain, or critical infrastructure use cases.
• Programming: Expert-level Python programming (pandas, scikit-learn, statsmodels, PyTorch/TensorFlow).
• Platform Expertise: Deep, hands-on experience with Databricks and the AWS cloud ecosystem.
• Mathematical Foundation: Strong understanding of probability, time-series analysis, and constrained optimization problems.
• Problem Solving: Ability to translate ambiguous business into structured mathematical frameworks.
• Experience in Energy & Utilities industry is a definite advantage.