Lead Machine Learning Engineer

About the Role 

We’re looking for a seasoned Machine Learning Engineer to lead the Machine Learning function within the Marketing Intelligence Team at Morningstar. This role will play a critical role by setting the requirements for the ML models, building the data pipelines and flows to power the model, as well as output model data that can be visualized and shared to business leaders. You will have deep technical data engineering skills and vision to build the machine learning road map. You will ensure models align to business goals, and are responsible for refining methodologies, iterating on models, and fine-tuning the model output. You will share out model findings to business stakeholders and tune and monitor models. You will evangelize model findings and feature engineering insights to marketing stakeholders and facilitate opportunities for stakeholders to use model output to deliver stronger business outcomes. 

To foster continuous collaboration, we follow a hybrid policy of a minimum of 3 days onsite in our Chicago office.

Responsibilities 

• Build, fine-tune, and implement machine learning models to answer challenging business questions 
• Ensure machine learning production pipelines are scalable, repeatable, and cloud agnostic 
• Apply current and emerging techniques in deep learning, AI, and other machine learning areas  
• Collect, clean, manage, analyze, and visualize large sets of data using multiple data platforms, tools, and techniques
• Optimize and fine-tune ML models for performance and scalability. Analyze and interpret data to extract meaningful insights and improve ML models 
• Maintain a database of model outputs, which will be used by the rest of the Marketing Intelligence team 
• Integrate ML solutions into Marketing Intelligence workstreams 
• Document and present findings and solutions to leaders and stakeholders 

Requirements 

• Master’s degree preferred, ideally in statistics, finance, mathematics, engineering, analytics, or in a quantitative discipline 
• 7+ years proven experience building data science models and executing data engineering work 
• Extensive experience in machine learning and statistical techniques, including regression, classification, clustering, time series forecasting, text analytics, and causal inference, and scaling end to end solutions 
• Expertise in marketing analytics & experimentation, such as Marketing Mix Modeling (MMM), Attribution Modeling, Lead Score Propensity Modeling
• Proficiency in Python, R, and SQL, with strong scripting capabilities to process and transform data for modeling 
• Strong background in big data processing and engineering using Apache Spark, PySpark, and Airflow, with experience in data lakes and warehousing solutions (Snowflake, Databricks, Redshift, BigQuery) 
• Experience with MLOps and cloud platforms (AWS SageMaker, Bedrock, Google Vertex AI, Azure ML), with a track record of automating machine learning pipelines and building end-to-end ML products 
• Hands-on experience with machine learning libraries, including Scikit-learn, Pandas, NumPy, Matplotlib, SciPy, Seaborn, XGBoost
• Hands-on experience with deep learning frameworks (TensorFlow, PyTorch) 
• Outstanding analytical and problem-solving skills with technical knowledge of setting requirements, working with complex data, and leveraging data stored across multiple data environments
• The ability to solution alongside team members and thrive in a collaborative environment, and convey complex concepts in a clear and concise manner