Quantitative / Machine Learning Engineer

TotalEnergies is a company expanding its activities in the power sector, focusing on renewable generation and power supply. The Quantitative / Machine Learning Engineer role involves developing advanced quantitative and machine-learning solutions to support trading and optimization in European short-term power markets. The engineer will work within the Trading & Shipping division, collaborating with various specialists to enhance trading performance. The main day-to-day responsibilities include developing and optimizing quantitative and machine-learning models for algorithmic trading. This involves the full lifecycle of model development, from data preparation and feature engineering to live deployment. The engineer will also design new indicators and signals, analyze complex datasets, and conduct research on European power markets. Additionally, they will monitor model performance, assess model behavior, and contribute to rigorous back-testing and validation methodologies. Collaboration with cross-functional teams is crucial for bringing models into production and ensuring their reliability and scalability. To qualify for this role, candidates must have an engineering degree, Master's, or PhD in a quantitative field such as Mathematics, Physics, Machine Learning, or Computer Science. Approximately 2–3 years of professional experience with machine-learning models in production, particularly in live forecasting or real-time applications, is required. Strong proficiency in Python, experience with MongoDB, SQL, and Shell scripting, and a solid understanding of software architecture and production-quality development practices are essential. Familiarity with Docker and DevOps/MLOps environments, including CI/CD pipelines, is also necessary. Additionally, strong knowledge of machine-learning techniques, including supervised and unsupervised learning, and practical experience with time-series modeling and analysis are must-haves. Nice-to-have skills include previous exposure to energy, commodities, or financial markets, and an understanding of European power markets. Experience with trading signals, forecasting models, or optimization problems, as well as familiarity with project-management and collaborative tools, are also beneficial. The role is based in a fast-paced, collaborative trading environment, offering significant exposure to live energy markets and the opportunity to work on models that directly impact trading performance. What the role asks for: - Engineering degree, Master's or PhD in a quantitative field such as Mathematics, Physics, Machine Learning, Computer Science or related discipline. - Approximately 2–3 years of professional experience working with machine-learning models in production, ideally involving live forecasting or other real-time applications. - Strong proficiency in Python. - Experience with MongoDB, SQL and Shell scripting. - Solid understanding of software architecture and production-quality development practices. - Experience with Docker and familiarity with DevOps/MLOps environments, including CI/CD pipelines. - Strong knowledge of machine-learning techniques, including supervised and unsupervised learning. - Practical experience with time-series modelling and analysis. - Nice-to-have: Previous exposure to energy, commodities or financial markets.