Requisition 40325: Lead Data Scientist - Machine Learning

Job Description

Norfolk Southern is seeking a Lead Data Scientist - Machine Learning to lead the design, development, deployment, and monitoring of advanced machine learning solutions that drive operational efficiency, safety, reliability, and business value across the enterprise.

This role combines deep technical expertise in machine learning with strong leadership and business engagement skills. The Lead Data Scientist will work closely with Data Engineering, Business Intelligence, Software Engineering, and business stakeholders to identify opportunities, develop scalable solutions, and mentor a team of data scientists. This position will focus on Machine Learning models (regression, classification, clustering, etc.) and it will not have a Computer Vision focus. Hands-on role requiring the individual to conduct research, develop and deploy analytical models, and take partial ownership of productionization activities to ensure successful implementation of solutions.

Who we are and what we do:
The AI and Data Science team is centralized across the entire organization. We work with various product teams across various business units to define high-impact business problems, solve them using novel techniques, and execute and monitor them throughout their lifecycle. Most of our models make it to production, they never sit in a research lab. But we also do quite a bit of research to stay up-to-date with the latest technologies/algorithms. We are very collaborative; you will likely get lots of ideas from the team.

What kind of problems do we solve:
There are high-frame cameras beside our tracks, capturing images of trains and rail cars as they pass. We design various Deep Learning and Computer Vision algorithms to detect certain objects of interest or issues and defects. We then optimize their performance and deploy them at the edge for real-time scoring and notification of our mechanical personnel upon detections. Our locomotives stream 350+ sensor information in real-time. We create predictive models to predict various component failures hours, days, and sometimes months in advance. The team is responsible for modeling operational data to develop data-driven solutions for network optimization problems, including ETA prediction and other transportation and logistics use cases. The team provides a wide range of ad hoc analytical support and insights to diverse stakeholder groups.

Responsibilities
• Lead the design, development, validation, and deployment of machine learning solutions.
• Architect end-to-end ML workflows from data acquisition through production deployment and monitoring.
• Establish standards and best practices for model development, experimentation, testing, and governance.
• Drive adoption of modern ML methodologies and tools across the organization.
• Effectively utilize appropriate statistical, Machine Learning, and Deep Learning techniques to solve various business problems
• Collaborate with various departments to identify opportunities for process improvement and developing analytics use-cases.
• Provide guidance, support and mentoring to junior team members.
• Evaluate accuracy and quality of data sources, as well as the designed models
• Stay up to date with the latest models and changes in technology
• Design and develop (almost) production ready code.
• Communicate results to colleagues and business partners.
• Coordinate with application development teams to integrate developed models with existing applications.
• Mentor and coach data scientists and machine learning engineers.

Education Required
• Master's or Ph.D. in Computer Science, Electrical Engineering, Machine Learning, Statistics or related field, OR Bachelor's degree with 7+ years related machine learning experience.

Skills Required:
• 7+ years of experience as a Data Scientist, Research Scientist, Machine Learning Engineer or Computer Vision Scientist.
• Demonstrated expertise in machine learning and/or deep learning methodologies, including model development, optimization, and deployment, utilizing algorithms, frameworks, and tools (e.g. XGBoost, LightGBM, Randon Forests, SVMs, clustering, dimensionality reduction, and neural networks).
• Advanced Python expertise is required, with a strong focus on modeling, data analysis, and visualization.

Skills Preferred:
• Advanced degree, e.g., Ph.D. or M.S. in deep learning, neural networks, machine learning, data science, computer science, electrical engineering, engineering, statistics, engineering, industrial systems, mathematical sciences, applied mathematics, Physics or or related technology-mathematics field.
• 3+ years of experience as a Data Scientist, Research Scientist, Machine Learning Engineer, or Operations Research.
• Hands-on and theoretical knowledge of various machine learning and deep learning algorithm and frameworks such as: xgboost/LightGBM, Random Forests, SVMs, PCA, t-sne, kmeans, DBSCAN.
• Knowledge of Spark (PySpark) is a plus
• Knowledge of the cloud computing environment (e.g. Databricks) is a plus
• Expertise with Time Series problems.
• Familiarity with the railroad or transportation industry is a plus

Work Conditions
Environment: Hybrid 2 days on-site and remote work 3 days per week.
Shift Work: No
On-Call: No
Weekend Work: No