Job Description

What are we looking for?

We are looking for a Data Scientist based in Sao Paulo. You will join our Data Science team, which works hand in hand with our asset monitoring platform. This platform tracks the real-time operation of the plants in the portfolio: generation, inverters, string boxes, trackers, and meters, as well as fault alerts and anomaly detection. The team is also responsible for processing and making available the plants data, with high-volume time series, on our analytics platform.

The next step is to turn this volume of data into predictive intelligence. We are looking for a data scientist to join the team in developing Machine Learning and Deep Learning models applied to plant operations and energy market modeling.

What challenges will you face?

• Develop predictive and preventive maintenance models for equipment (inverters, trackers, string boxes, BESS) based on historical operation, event, and failure data.
• Build fault and anomaly detection and classification models for production. The goal is to separate real issues from noise, communication intermittency, and false positives, thereby improving the quality of alerts delivered to operations.
• Build short- and medium-term generation forecasting models, combining historical plant data with weather forecasts (irradiance, temperature, cloud cover, etc.).
• Conduct plant performance analyses (performance ratio, temperature losses, soiling, unavailability, clipping, among others) and explain deviations between expected and actual generation.
• Collaborate with the team's data engineering in the preparation, quality, and modeling of the time series data that feed the models.
• Bring models into production together with the team, including monitoring, versioning, and retraining, integrating results into the monitoring platform.
• Work in the future on energy market modeling: price forecasting, dispatch curve analysis, and optimization of battery storage (BESS) asset operations.
• Work closely with operations and maintenance (O&M), engineering, and business teams to understand real problems and turn them into data-driven solutions.

What specific knowledge do you need?

• Degree in Engineering, Computer Science, Statistics, Mathematics, Physics, or related fields.
• Prior experience with data science and Machine Learning model development, in a professional, academic, or substantial personal-project setting.
• Proficiency in Python and the data/ML ecosystem: pandas/polars, scikit-learn, and at least one Deep Learning framework (PyTorch or TensorFlow).
• Experience with time series: forecasting, anomaly detection, and temporal feature engineering.
• Good working knowledge of SQL and experience with relational databases (preferably PostgreSQL).
• Solid foundation in statistics and model evaluation (temporal validation, metrics, overfitting, class imbalance).
• Use of Git and good coding practices.
• Ability to communicate technical results clearly to non-technical audiences.

What does Atlas offer you?

• Belong to a multicultural, inclusive, and diverse environment. We are in the USA, Mexico, Brazil, Chile, Uruguay, Colombia,.
• Be part of a company that promotes flexibility: work by objectives and have a hybrid/flexible work style (home-office or in the office) in coordination with your supervisors.
• Twenty work days of vacation (which you can take in advance without completing the year) and additional rest days for the end-of-the-year holidays.
• Other economic benefits include performance bonuses and food vouchers.
• We promote sports with our "In Motion" benefit.
• We promote Health and Life with our health and life insurance with high-level coverage.
• Access to a large and diverse volume of real plant operation data.
• Lean technical team, with autonomy and room to propose and build solutions from scratch.
• Multicultural, collaborative environment, with exposure to professionals from multiple countries