Staff Data Scientist
Description
Enphase Energy is a global leader in solar inverters. By combining the power of solar energy and the proven advantages of communications technology, Enphase Energy makes solar power systems productive, reliable, smart and safe - increasing the energy harvest of solar panels by up to 25 percent. Our microinverter system is profoundly changing the way solar systems function, and thus, changing the solar industry itself.
As we continue our exciting growth, we are building teams with highly talented individual contributors and leaders who design, develop, and manufacture next generation solar technologies. Our work environment is fast-paced, fun, and full of exciting new projects.
The Sr. Data Scientist will be responsible for analyzing product performance in the fleet. Provides support for the data management activities of the Quality/Customer Service organization. Collaborates with Engineering/Quality/CS teams and Information Technology.
Requirements of this role
- Strong understanding of industrial processes, sensor data, and IoT platforms, essential for building effective predictive maintenance models.
- Experience translating theoretical concepts into engineered features, with a demonstrated ability to create features capturing important events or transitions within the data.
- Expertise in crafting custom features that highlight unique patterns specific to the dataset or problem, enhancing model predictive power. Ability to combine and synthesize information from multiple data sources to develop more informative features.
- Advanced knowledge in Apache Spark (PySpark, SparkSQL, SparkR) and distributed computing, demonstrated through efficient processing and analysis of large-scale datasets. Proficiency in Python, R, and SQL, with a proven track record of writing optimized and efficient Spark code for data processing and model training.
- Hands-on experience with cloud-based machine learning platforms such as AWS SageMaker and Databricks, showcasing scalable model development and deployment.
- Demonstrated capability to develop and implement custom statistical algorithms tailored to specific anomaly detection tasks.
- Proficiency in statistical methods for identifying patterns and trends in large datasets, essential for predictive maintenance. Demonstrated expertise in engineering features to highlight deviations or faults for early detection. Proven leadership in managing predictive maintenance projects from conception to deployment, with a successful track record of cross-functional team collaboration.
- Experience extracting temporal features, such as trends, seasonality, and lagged values, to improve model accuracy. Skills in filtering, smoothing, and transforming data for noise reduction and effective feature extraction.
- Experience optimizing code for performance in high-throughput, low-latency environments. Experience deploying models into production, with expertise in monitoring their performance and integrating them with CI/CD pipelines using AWS, Docker, or Kubernetes.
- Familiarity with end-to-end analytical architectures, including data lakes, data warehouses, and real-time processing systems.
- Experience creating insightful dashboards and reports using tools such as Power BI, Tableau, or custom visualization frameworks to effectively communicate model results to stakeholders.
- 6-8 years of experience in data science with a significant focus on predictive maintenance and anomaly detection.
Qualifications
- Bachelor’s or Master’s degree/ Diploma in Engineering, Statistics, Mathematics or Computer Science
- 6+ years of experience as a Data Scientist
- Strong problem-solving skills
- Proven ability to work independently and accurately