Data Scientist – Predictive Maintenance

• Develop time-series ML models for anomaly detection, forecasting, behavioral modeling, and condition monitoring using large-scale industrial sensor data.
• Translate experimental models into reliable, maintainable, and scalable production systems.
• Design metrics, diagnostics, and monitoring mechanisms for data quality, feature distributions, anomaly scores, prediction stability, model drift, and performance.
• Investigate modeling strategies balancing predictive performance, generalization, adaptability, interpretability, and maintenance costs.
• Develop feature extraction, signal processing, and representation learning techniques for industrial sensor data.
• Formulate hypotheses, design controlled experiments, benchmark approaches, and evaluate models using temporal validation and realistic deployment scenarios.
• Improve data processing, feature computation, model serving, and inference workflows for high-throughput, low-latency applications.
• Evaluate state-of-the-art methods and translate promising techniques into production-ready solutions.
• Collaborate with software engineers, product teams, and laboratory specialists to validate models, investigate failures, and improve predictive maintenance products.

• Strong background in machine learning, with practical experience developing models for time-series data, anomaly detection, forecasting, or related sequential modeling problems.
• Proficiency in Python and common ML and data processing libraries, such as NumPy, pandas, scikit-learn, PyTorch, or equivalent frameworks.
• Experience taking machine learning models from experimentation to production, including code organization, testing, performance optimization, and integration with data or inference pipelines.
• Solid understanding of time-series fundamentals, including temporal dependencies, non-stationarity, seasonality, noise, and appropriate validation strategies.
• Understanding of data drift and model degradation in production, including techniques for monitoring distribution shifts, evaluating model stability, and identifying when model updates are necessary.
• Strong software engineering skills, including writing modular, testable, maintainable code and designing solutions that can operate reliably at scale.
• Experience designing experiments and benchmarking models using appropriate metrics, baselines, and validation methodologies.
• Ability to analyze complex, noisy, high-dimensional data and translate empirical findings into sound technical decisions.
• Proficient in English and Portuguese.

• Competitive Compensation
• 30 days of paid annual leave
• Education and courses stipend
• Earn a trip anywhere in the world every 4 years
• R$1.035/month for meals allowance
• Health plan with national coverage and without coparticipation
• Dental Insurance: we help you with dental treatment for a better quality of life.
• Wellhub Membership: Access a wide range of gyms and training programs.