Sr. Data Scientist - Supply Chain

US Foods•Illinois Virtual Location, IL

10d•$100,000 - $155,000•Remote

About The Position

The Sr Data Scientist – Supply Chain role will lead forward-looking analytics initiatives across time series forecasting, supply chain demand, buying, and inventory optimization, including data exploration, decision modeling, statistics, measurement sciences, and machine learning operations. The main responsibilities include, but are not limited to, developing and productionalizing customized forecasting and optimization models that improve demand accuracy, inform buying decisions, and right-size inventory, while enhancing supply chain replenishment by balancing a breadth of constraints, variables, and cost considerations. This role requires a deep analytical, technical, and complex problem-solving skill set with expertise in time series forecasting, mathematical optimization, statistical analysis, and advanced machine learning and deep learning techniques. The Sr Data Scientist proactively works with cross-functional teams to understand the business context of supply chain problems that may be solved using ML and optimization, and presents data science solutions to stakeholders in an iterative fashion. They work with Associate Data Scientists, Data Scientists, and Decision Scientists to translate business challenges into well-structured forecasting, optimization, or ML problems, kickstarting foundational work including data exploration, feature engineering, hypothesis testing, and baseline modeling. They play a key role in selecting and implementing the appropriate analytical approach and create the model feasibility document in close collaboration with the team. The Sr Data Scientist may have direct reports including Associate Data Scientists and Data Scientists. The work for the Sr Data Scientist position is completely remote anywhere in the United States except Hawaii or United States Territories.

Requirements

Master’s degree in data science/mathematics/CS/statistics or similar field and 3+ years of experience OR Bachelor's degree and 6+ years of experience in data science
Effective written, verbal, and interpersonal communication skills, with the ability to work and communicate effectively with team members and cross-functional teams
An expert-level understanding of the following topics: Classification, Regression, Clustering, Dimensionality reduction, Association rule learning, Bagging (e.g., Random Forests), Boosting (e.g., AdaBoost, Gradient Boosting), Neural Networks and Deep Learning, Model Evaluation and Metrics, Cross-validation, Hyperparameter Tuning, Optimization Algorithms, NLP and more
Working knowledge of Agile/SCRUM methodologies with 1-2 years of experience and a practical understanding of the epics, features, and tasks that may be most relevant and how much effort is required for them
Sufficient intellectual curiosity to investigate the latest developments in the field (for example LLM/Generative AI models)
Ability to see the big picture and anticipate issues in terms of deployment limitations, data latency, appropriateness of a particular implementation of algorithms, and mathematical details/assumptions
At least 1+ years of working with a major cloud platform, creating ML models using frameworks from data exploration to deployment
Working knowledge in handling large datasets in a cloud environment
Working knowledge of how APIs work, CI/CD (Continuous Integration/Continuous Deployment)
Understanding of DevOps and MLOps principles
1+ years of writing production-grade code in scripting languages including Bash, Python, and SQL with the ability to identify the areas of improvement, optimal choice of data structures, optimization of the code, and creating custom code to address unique situations
Proven, independent ability to navigate a data lake environment while creating training datasets or feature stores
Effective skills in creating, deploying, and troubleshooting containers in the context of ML modeling
1+ years of experience with version control systems/concepts, such as Git, for tracking changes in machine learning projects
Ability to investigate/research ML frameworks/algorithms, datasets, feature stores, and contribute to solving data science problems
Capability of providing macro-level thought leadership to the junior members including the Data Scientists regarding best practices, issues, causes, and respective resolutions of those issues

Nice To Haves

2 years of supply chain analytics experience, preferably in replenishment systems, time series forecasting, order optimization, network optimization, inventory management, and/or logistics
Preferred 1+ year of Optimization & Operations Research experience with experience writing production-grade code in optimization modeling languages; Gurobi, Pyomo, PuLP, etc.

Responsibilities

Work with Associate Data Scientists and Data Scientists in researching data sources, data cleansing, feature engineering, and creating baseline models
Independently lead the formulation and development of forecasting, optimization, and ML models while managing multiple model development projects
Design, implement, and refine advanced ML and deep learning models for both time series forecasting and optimization to solve large-scale, real-world supply chain demand, buying, inventory, and replenishment problems
Collaborate and engage with various cross-functional stakeholders to ensure close coordination between data science and business stakeholders including the product management team
Provide full ownership of the model development from inception to implementation including the machine learning pipeline, documentation, model drift, and remodeling strategy
Mentor the Associate Data Scientists and Data Scientists in data science knowledge and their interactions with other stakeholders
Coordinate with the ML team, anticipating deployment issues upfront, setting the stage for resource requirements, and ensuring the success of model deployment and retraining
Take and delegate ownership of critical tickets or issues faced by business stakeholders as assigned by the Lead Data Scientist or Director of Data Science
Read and independently navigate through extensive codebase with a focus on troubleshooting, debugging, and/or improvement of code
Contribute to coding standards and coding conventions and proactively participate in enforcing sound coding practices across the data science team
Create and maintain documentation of the ML models, data sources, and methodology
Assist in the creation of feasibility documents
Proactively participate in the core team processes including R&D, recommending, and implementing process improvements or new methodologies
Share knowledge with other various teams and members by presentation at periodic internal team sessions/workshops
Guide usage of development methodologies (Scrum, Kanban, etc.) and assist in their implementation in the group projects by deciphering details including features, tasks, estimates of efforts and timing, etc.