Job at a glance
Role: Data Scientist Location: US Remote This resource will work specifically on anomaly detection within one of our plant operations projects. The purpose of this project is to scale anomaly detection models for the transformer fault POC and add new models relating to thermal data. Other projects as required to require skills in forecasting and linear regression. Essential Duties/Responsibilities: Understanding of machine learning and deep learning models to select and implement for prediction, classification, and clustering Understanding of the business context of projects and able to identify areas where models will be less predictive or have caveats to their predictive powers Ability to communicate and establish good relations with multi-disciplinary teams Expertise with neural networks, specifically RNNs within the Keras/TensorFlow framework.
Proficiency with Python, including pandas, scikit-learn Experience in PySpark Minimum Requirements: Bachelors degree in a quantitative field, such as Statistics, Mathematics, Computer Science, Economics, Engineering, or Operations Research required. 3+ years of experience in statistical modeling and quantitative analysis in industry or full-time academic research Preferred Qualifications: Advanced Degree (MS or PhD) in Statistics, Mathematics or Quantitative Marketing with a focus on machine learning is strongly preferred.
Additional Knowledge, Skills and Abilities: Knowledge of power transformers, experience with electrical engineering. Prior experience predictive maintenance in a power or manufacturing environment. Experience with Databricks, AWS SageMaker and/or Google Vertex AI Comfortable working in Linux Experience with Git Experience with Docker containers Good communication skills