Lead Data Scientist

About the position

Welcome to Resideo, where we're on a mission to transform homes into intelligent, efficient, and secure homes through the power of IoT-connected devices. As a Lead Data Scientist on our Data team, you'll play a pivotal role in extracting actionable insights from complex time-series data, making a direct impact on the comfort and safety of homes worldwide. As part of this initiative, we are looking for a Lead Data Scientist to help lead our Water data team in developing intelligent water monitoring and protection systems. You'll be at the forefront of applying advanced machine learning techniques to analyze real-time sensor data streams that help protect homes from water damage. Our systems must precisely differentiate between normal household water usage and anomalous events, while maintaining high accuracy to ensure customer satisfaction. Success in this role comes from combining deep data science expertise with strong product intuition to deliver scalable, production-ready solutions that provide value to both our professional installers and homeowners.

Responsibilities

• Own and drive the performance of machine learning models for water monitoring systems, including metrics definition, monitoring, and continuous improvement strategies
• Lead end-to-end machine learning development from research through production deployment, making independent technical decisions to support program growth
• Provide technical and strategic leadership to the data team, operating autonomously to deliver on Water business unit objectives
• Build and maintain key relationships across Product Management, Engineering, and Business teams to identify opportunities
• Set technical direction for the team, taking full ownership of product performance
• Mentor team members and foster a culture of innovation while maintaining high standards for production ML systems
• Familiarity with modern ML frameworks and libraries including, deep-learning (e.g., TensorFlow, Keras, or PyTorch), Scikit-learn, Numpy, Pandas, and MLFlow.

Requirements

• 7+ years of industry experience using Python, R, etc. working with (preferably) time-series data to support data analysis, visualization, exploratory data analysis, feature generation, and model fitting (in addition to other common analysis activities common to machine learning)
• Expert in at least one programming language for data analysis (e.g., Python, R), experience with SQL a plus
• Experience working with Apache Spark (preferably PySpark)
• Strong foundation in machine learning and statistical modeling
• Industry experience with developing and applying machine learning and statistics in at least one of the following categories: Anomaly detection, Image processing (e.g. convolutional neural networks, auto-encoders), or time-series methods

Nice-to-haves

• Candidate should have project management experience and the ability to work in a fast-paced, high-visibility environment
• Experience with water flow systems, HVAC, or related industrial applications
• Experience with consumer facing IoT Products
• Knowledge and experience with Databricks, Jupyter notebooks, Git, AWS or Azure cloud environments
• A continuous learning mindset with a willingness to stay updated with the latest trends and technologies in data science and machine learning.