Overview
Design, build and productionize machine learning and AI solutions for S&P Global Commodity Insights' Data Science & Modelling team, working across machine learning, software engineering, data engineering and domain modelling.
What you'll do
- Design, develop and productionize scalable machine learning and AI solutions for complex business and modelling problems.
- Build robust data and ML pipelines covering data preparation, feature engineering, training, deployment, evaluation and monitoring.
- Develop high-quality, reusable Python software and services that integrate ML capabilities into production applications and analytical platforms.
- Work with large and complex structured and unstructured datasets to improve the quality, accuracy and intelligence of products and modelling capabilities.
- Apply modern ML techniques, and where appropriate Generative AI, LLMs and agent-based approaches, to solve business and domain problems.
- Establish and apply strong MLOps and software engineering practices, including automated testing, CI/CD, versioning, observability and reproducibility.
- Build solutions using modern cloud and distributed-computing platforms.
- Evaluate model quality and system performance using appropriate quantitative metrics, validation frameworks and monitoring.
- Collaborate closely with data scientists, modelers, data engineers, product teams and energy-domain experts to translate business and modelling requirements into robust technical solutions.
- Investigate emerging ML and AI technologies and identify practical opportunities to apply them within Data Science & Modelling.
- Contribute to engineering standards, architecture decisions, code reviews and technical mentoring across the team.
What you'll need
- 3+ years of professional software development or engineering experience, with strong proficiency in Python.
- Demonstrated experience designing and implementing production-grade machine learning or advanced analytical systems.
- Strong knowledge of software engineering fundamentals, including object-oriented design, modular architecture, testing, clean-code practices and design patterns.
- Experience working with SQL and large-scale data platforms.
- Experience building scalable data processing and ML pipelines using technologies such as Apache Big data processing engines and Databricks or comparable platforms.
- Experience deploying and operating solutions in a cloud environment such as AWS.
- Understanding of the ML lifecycle, including training, validation, deployment, monitoring and model/version management.
- Experience with modern engineering and DevOps practices including Git, automated testing, CI/CD and containerization.
- Ability to design reliable, performant and maintainable systems handling large or complex datasets.
- Strong analytical and problem-solving skills.
- Ability to communicate effectively with both technical and non-technical stakeholders and work successfully in cross-functional Agile teams.
- Bachelor's or advanced degree in Computer Science, Engineering, Mathematics, Data Science or a related quantitative discipline, or equivalent practical experience.
Nice to have
- Experience working with energy, oil & gas, commodities or financial/market data.
- Experience with Databricks and modern lakehouse architectures.
- Experience building or integrating Generative AI, LLM, RAG or agentic AI solutions.
- Experience with ML lifecycle and orchestration technologies such as MLflow, Airflow or equivalent platforms.
- Experience with model evaluation, observability and production monitoring.
- Experience developing APIs or services for integrating ML capabilities into production applications.
- Familiarity with deep-learning frameworks such as PyTorch or TensorFlow.
- Experience working with time-series forecasting, optimization, simulation or other advanced modelling techniques.
Read the full description and apply on the company’s own careers page.