DescriptionVortexa is a fast-growing international technology business founded to solve the immense information gap that exists in the energy industry. By using massive amounts of new satellite data and pioneering work in artificial intelligence, Vortexa creates an unprecedented view on the global seaborne energy flows in real-time, bringing transparency and efficiency to the energy markets and society as a whole. Ingesting data from multiple external vastly different sources at hundreds of rich data points per second, moving terabytes of data while processing it in real time, running complex and complicated prediction and forecasting AI models while coupling their output into a hybrid human-machine data refinement process and presenting the result through a nimble low-latency SaaS solution used by customers around the globe is no small feat of science and engineering. This processing requires a unique fusion of humans and machines, close collaboration between and deep expertise from data analysts, data scientists, industry experts and the end users. Vortexa's Data Platform, designed, developed and maintained by the Data Production Team, is a cloud-native ecosystem that powers the full lifecycle of our data and intelligence products. It integrates large-scale data pipelines, machine-learning models, AI agents, human-in-the-loop systems, and microservices to collect, process, connect, and govern global energy-flow data at scale. Our models ingest and interpret a diverse range of data, from satellite imagery and sensor feeds for millions of energy assets to unstructured commercial and operational shipping data such as customs filings, fixtures, and SPAs. These inputs drive predictive systems that support energy-demand forecasting, anomaly detection, and real-time recommendations for physical and derivative trading. As a Principal Data Scientist, reporting to Vortexa's VP of Data Production, you will be the subject-matter authority for data science - the person the company turns to on the problems no one has cracked yet - and you will play a central role in designing, implementing, and deploying advanced AI/ML methodologies and production-grade systems. Your work will be held to the scrutiny of energy analysts, traders, operations teams and regulatory stakeholders, and must meet the performance, reliability and robustness standards required for critical energy infrastructure. Taking problems end-to-end: moving across pods and owning substantial projects from initial exploration all the way through to long-term maintenance, ultimately delivering robust, production-grade solutions. Building the capability of Data Science: through technical review, pairing and mentoring, setting the standards for how we work, and by being the person analysts, engineers and product managers bring their hardest questions to. Leading the Data Science Guild: setting the technical agenda and creating the forum where the significant questions across the practice are surfaced, challenged and worked through. RequirementsYou Are A demonstrably strategic, high-impact individual contributor: experienced enough to lead complex projects across Data Science, Machine Learning and AI, while remaining hands-on and capable of building and deploying production-grade models. Deeply grounded in ML/AI: strong in the theoretical and mathematical foundations of the field, with the ability to engage critically with current research and emerging methodologies. Engineering-grounded across the full ML lifecycle: comfortable owning your own code to production standard, from experiment design and model development through validation, deployment, monitoring and long-term maintenance. Deeply trained in a quantitative discipline, ideally educated to PhD level in Computer Science, Statistics, Applied Mathematics, Physics or a related field. Fluent in Python and broad in your modelling toolkit: with strong experience across regression and classification, clustering, time-series analysis, anomaly detection, sequence-to-sequence architectures and stochastic optimisation. Your success is measured not only by what you personally ship, but by what the team is capable of doing a year after you arrive. Have quantitative trading experience: particularly around arbitrage, strategy development, backtesting and risk management across physical or derivative assets. Have worked with frontier AI techniques: including transformer architectures, generative models or agentic AI, particularly where models need to operate reliably in operational or time-sensitive environments. BenefitsEnjoy flexible hybrid working – split your time between home and our office, with the freedom to work where you're most productive. A vibrant, diverse company pushing ourselves and the technology to deliver beyond the cutting edgeA team of motivated characters and top minds striving to be the best at what we do at all timesConstantly learning and exploring new tools and technologiesActing as company owners (all Vortexa staff have equity options)– in a business-savvy and responsible wayMotivated by being collaborative, working and achieving togetherPrivate Health Insurance offered via Vitality to help you look after your physical healthGlobal Volunteering Policy to help you 'do good' and feel betterJob SummaryID: C0C094AAF8Department:
Research Data Scientist - Machine Learning in London employer: Vortexa
Vortexa is an exceptional employer that champions innovation and growth in the energy sector, offering a dynamic work culture where employees can thrive in their product management careers. With a commitment to employee well-being, Vortexa provides flexible hybrid working arrangements, private health insurance, and opportunities for global volunteering, ensuring that team members are supported both personally and professionally. Join us to be part of a forward-thinking company that values creativity, collaboration, and continuous learning in a fast-paced scale-up environment.
