Senior Data Scientist

Johnson Controls•Glendale, CA

37d•Hybrid

About The Position

Johnson Controls is a global leader in smart, healthy, and sustainable buildings, serving customers in more than 150 countries. We create intelligent buildings, efficient energy solutions, integrated infrastructure, and next-generation transportation systems. Johnson Controls is seeking a Senior Data Scientist with a strong practical background in deploying production-ready AI/ML solutions. This role focuses on developing advanced agentic AI systems, time series analytics, and signal processing capabilities to optimize our building technologies, HVAC systems, and industrial IoT platforms. This is a hybrid position (onsite 3 days per week) based in Glendale, WI. Candidates must be commuting distance, or able to relocate.

Requirements

Bachelor's degree in Data Science, Computer Science, Engineering, Statistics, or related field
7+ years of professional experience developing and deploying ML/AI solutions in industrial, IoT, or similar environments
Experience delivering at least 2-3 production ML models with measurable business impact
Hands-on experience building agentic AI systems or autonomous decision-making algorithms
Knowledge of reinforcement learning, multi-agent systems, or autonomous optimization frameworks
Exposure to LLM-based agents, tool use, or reasoning frameworks for decision-making
Solid understanding of supervised and unsupervised ML algorithms with deployment experience
Experience with time series forecasting using methods like ARIMA, Prophet, LSTM, or similar approaches
Hands-on work with seasonal patterns, trend analysis, and time series decomposition
Experience applying time series techniques to real-world datasets (sensor data, energy consumption, etc.)
Familiarity with handling missing data, outliers, and non-stationary time series
Working knowledge of digital signal processing including filtering, FFT, and spectral analysis
Experience processing sensor data from industrial equipment (vibration, temperature, pressure, acoustic signals)
Ability to implement feature extraction from signal data and apply noise reduction techniques
Understanding of frequency domain analysis and pattern detection in signals
Strong proficiency in Python with ML libraries (scikit-learn, TensorFlow or PyTorch, XGBoost)
Experience with signal processing libraries (scipy.signal, PyWavelets)
Working knowledge of time series libraries (statsmodels, Prophet, or tslearn)
Experience with at least one cloud platform (Azure preferred, AWS, or GCP)
Solid SQL skills and familiarity with data streaming technologies (Kafka, MQTT)
Version control with Git and basic MLOps practices

Nice To Haves

Azure Machine Learning Experience with Azure Machine Learning workspace, automated ML, or deployment capabilities
Familiarity with Azure ML pipelines, model registry, or managed endpoints
Exposure to Azure Databricks, Azure Synapse Analytics, or Azure IoT Hub
Basic knowledge of Azure DevOps for CI/CD or model versioning
Exposure to genetic algorithms or evolutionary strategies for optimization problems
Experience applying evolutionary computation for hyperparameter tuning or feature selection
Interest in nature-inspired algorithms and optimization techniques
Experience contributing to predictive maintenance projects or failure prediction models
Knowledge of remaining useful life (RUL) estimation or anomaly detection in equipment data
Understanding of condition-based monitoring concepts
Familiarity with maintenance optimization approaches

Responsibilities

Design and deploy agentic AI systems that autonomously optimize building operations, energy consumption, and equipment performance
Develop and implement advanced time series forecasting models for energy demand, equipment behavior, and operational patterns
Apply signal processing techniques to analyze sensor data, detect anomalies, and extract meaningful patterns from noisy industrial environments
Build end-to-end machine learning pipelines from data ingestion through model deployment and monitoring in production systems
Lead predictive maintenance initiatives using ML models to forecast equipment failures and optimize maintenance schedules
Collaborate with engineering and operations teams to translate business problems into practical data science solutions
Mentor junior data scientists and establish best practices for model development and deployment