Data Scientist - Power Systems & Machine Learning

About the role

Enline combines power systems engineering, AI and high-performance simulations to give grid operators and renewable producers actionable recommendations for asset control and optimisation. It is looking for a Data Science / Machine Learning Engineer with a solid grounding in power systems to own the analytical and predictive models behind its products, from first prototype to production. The role improves the algorithms used by current clients, brings in new data sources such as satellite imagery and works alongside power systems engineers so that the models respect the physics of the network.

Key responsibilities

• Develop the analytical and predictive models behind Enline's products.
• Collect relevant data, pre-process it and carry out exploratory data analysis.
• Apply data modelling, statistical and machine learning techniques to build predictive models, including time series forecasting.
• Take models into production and improve existing algorithms to meet the needs of current clients.
• Work with power systems engineers, bringing power flow and system analysis knowledge into the models.
• Provide AI-related technical support to the commercial team.
• Communicate the results of analyses and models clearly and concisely to management and other stakeholders.

Required profile

• Proven data science experience of 2+ years.
• Strong programming skills in Python, R or another relevant language.
• Experience handling large datasets and data storage systems, with knowledge of relational and non-relational databases.
• Knowledge of statistics, including hypothesis testing, ANOVA, regression and linear models.
• Solid knowledge of power flow and system analysis, and understanding of transmission and distribution systems.
• Interest or experience in the energy sector.
• Fluent technical English; Portuguese or Spanish is a plus.

Nice to have

• Experience developing electrical studies.
• Cloud platforms such as AWS, GCP or Azure.
• Image processing techniques (segmentation, object detection, classification, pattern recognition).
• Geospatial data libraries and large-scale, complex APIs.
• Docker, Kubernetes and agile software development teams.