What are the responsibilities and job description for the Data Scientist II position at PODS?
Job Summary
PODS operations already run on data, and the planners and field leaders making the calls on positioning, routing, and capacity are good at it. Operations Data Science & AI is a new team built to turn that expertise into automated, optimized decision systems that run continuously, in every market.
As a Data Scientist on the team, you will report to the Director, Operations Data Science & AI and partner with engineers and operational stakeholders to develop optimization models, predictive models, and automated workflows. Your work will help PODS make better decisions across capacity planning, routing, scheduling, resource allocation, and other field operations.
Essential Duties And Responsibilities
PODS operations already run on data, and the planners and field leaders making the calls on positioning, routing, and capacity are good at it. Operations Data Science & AI is a new team built to turn that expertise into automated, optimized decision systems that run continuously, in every market.
As a Data Scientist on the team, you will report to the Director, Operations Data Science & AI and partner with engineers and operational stakeholders to develop optimization models, predictive models, and automated workflows. Your work will help PODS make better decisions across capacity planning, routing, scheduling, resource allocation, and other field operations.
Essential Duties And Responsibilities
- Develop optimization solutions:
- Build and support optimization models for capacity planning, routing, scheduling, and resource allocation.
- Formulate business problems using decision variables, objectives, and operational constraints.
- Assist in root-cause analysis to surface optimization and automation opportunities across field operations.
- Develop predictive models:
- Build, test, and maintain forecasting, regression, classification, and anomaly-detection models for operational problems.
- Prepare and validate data, engineer features, and evaluate model results.
- Build and automate workflows:
- Build reproducible data pipelines and automate recurring analyses, model runs, and reporting, replacing manual processes.
- Contribute to shared tooling, frameworks, and standards so that solutions are repeatable.
- Develop analytical assets and data models:
- Maintain data models in Snowflake that other analysts and downstream tools rely on.
- Create dashboards and decision-support tools that make results actionable.
- Document and communicate clearly:
- Document logic, methodology, and assumptions alongside every model, tool, or pipeline you build.
- Present findings and their limitations in plain language to the team and operational stakeholders.
- Mathematical optimization: Hands-on experience formulating and solving mixed-integer linear programming models, including defining decision variables, objectives, and constraints.
- Optimization tools: Previous experience with Gurobi, Pyomo, OR-Tools, PuLP, CPLEX, or a similar optimization library or solver is required.
- SQL and Python fluency: Strong SQL on a modern cloud data warehouse, preferably Snowflake, and Python for analysis and model development.
- Applied machine learning: Experience building, testing, and validating forecasting, regression, classification, or other predictive models, with judgment about which method fits the problem.
- Workflow automation: Experience building reproducible data pipelines and automating recurring analyses and model workflows.
- Data visualization: Ability to communicate analytical and model outputs through clear visualizations and practical decision-support tools.
- Communication and documentation: Ability to explain methods and results clearly and document work so that it is reproducible and reviewable.
- Structure amid ambiguity: Ability to turn loosely defined operational problems into clear analytical questions and practical solutions.
- Bachelor’s degree in a quantitative field such as Data Science, Statistics, Operations Research, Industrial Engineering, Applied Mathematics, Physics, Computer Science, Engineering, Economics, or a related field required; master’s degree preferred
- 3 years of applied data science, machine learning, or quantitative analytics experience. Relevant internship, co-op, or graduate research may count toward experience.
- Hands-on experience with SQL on a modern cloud data warehouse (Snowflake preferred) and with Python for analysis.
- Experience or coursework in machine learning and mathematical optimization, with exposure to cloud-based data platforms such as Snowflake or AWS.
- Experience supporting an Operations, Supply Chain, logistics, or other capacity-constrained business is a plus.
- Ability to sit at a desk and use a computer for up to 8 hours a day; Ability to use hands and fingers to type on a keyboard and use a mouse to navigate; Vision sufficient to view small details on a computer monitor
- Ability to stand and walk up to 8 hours a day; ability to stoop, bend and lift boxes weighing up to 50 lbs.
- Ability to hear and verbally communicate using a telephone handset and/or connected headset device
- Regular business hours. Some additional hours may be required.
- Travel requirements: Negligible
- Climate-controlled office environment during normal business hours.
- Regular attendance and punctuality required
- May be subject to pre-employment criminal background check and/or drug screening as well as random drug screenings in accordance with company policy