Location: Hershey, PA
This position will be Hybrid.
Summary:
This role within our Information Services department is looking for a Data Scientist that can apply scientific principles to analyze complex datasets across different groups to make business decisions. Develops scalable algorithms and models.
Major Responsibilities:
- Translates well-structured business problems into data science problems. Analyzes complex datasets to inform or make decisions to address those business problems.
- Applies scientific principles and concepts to support invention. Uses a range of scientific methodologies and follows best practices for those methodologies.
- Proactively identifies solutions to problems. Solutions may require novel techniques or approaches.
- Creates metrics and measurements to quantify the business impact of the work.
- Writes accurate and clear technical documentation and reports, including appropriate mathematical rigor as needed.
- Communicates the approach and outcomes of models clearly and effectively with non-technical stakeholders to build trust.
- Collaborates with stakeholders across a broad set of functions (science, data, engineering, product, business).
Scope:
- Influence is primarily within the team
- Deliver artifacts on medium size projects, define methodology and own analysis Results affect important business decisions.
- Influence teams technical and business strategy by making insightful contributions to team priorities and approach
- Develop metrics to quantify the benefits of a solution and influence project outcomes.
Qualifications:
- Data analytics skills and experience analyzing both experimental and observational data sets.
- Expertise in one or more of: machine learning, natural language processing, computer vision, operations research, applied mathematics, statistics, econometrics, causal analysis, or similar science discipline.
- Experience developing one or more of: A/B testing capabilities, forecasting models, inventory optimization, capacity planning, pricing, recommender systems, classification models, causal impact, customer choice models, or similar science products.
- Proficiency with math/stats software (e.g. R, Matlab, SAS, Stata, Python numpy) or other domain specific software (e.g. Python/TensorFlow for ML). Basic proficiency with SQL.
- Strong skills in model development, model validation, and model implementation. For ML-related roles, additional experience in model deployment and ongoing production support.
Experience and Education:
- Masters/PhD in a quantitative field (CS, CE, ML, OR, Econ, or related). PhD preferred
- Minimum of 3 years of experience in data science or a related field
#LI-SM1