Sr Data Scientist

The Hershey Company - Hershey, PA

Full-time - Mid Level

Hershey, PA

Food Manufacturing

About the position

The Procurement Data Science organization at Hershey is dedicated to driving value through the development of innovative predictive and prescriptive solutions that enhance analytics and decision-making across the Global Procurement organization. As a Senior Data Scientist, you will collaborate closely with business partners, technical engineers, data architects, and project managers to ensure that data science standards align with the company's best practices, ultimately delivering rapid and impactful benefits to the organization. In this role, you will serve as a trusted advisor to Hershey's business partners, leveraging your expertise to build new, data-driven, machine-intelligent capabilities that significantly influence business outcomes. You will be tasked with working with large datasets, recommending cutting-edge technologies, and employing advanced methodologies to address real-world business challenges. Your responsibilities will include designing and conducting experiments, researching new algorithms, and discovering innovative ways to optimize risk, profitability, and customer experience. You will also work alongside a diverse team of professionals, including business analysts, technical engineers, data architects, and project managers, to ensure that the outcomes align with the strategic goals of our business partners. Additionally, you will collaborate directly with the Director of Data Science to maintain consistency and compliance of deliverables with established frameworks and governance processes. This position requires a strong foundation in machine learning, statistical modeling, feature discovery and selection, optimization, exploratory data analysis, data mining, and pattern recognition.

Responsibilities

• Analyze the source to pay data landscape to develop the Global Procurement Data & Technology roadmap using best practice data science methods, frameworks, and governance processes
• Collaborate with IT and business partners to define, manage and deliver innovative data science solutions to drive growth and adoption of capabilities at Hershey
• Evangelize future data science solutions identified by Enterprise Data leadership, including innovations such as machine learning, statistical modeling, feature discovery/selection, optimization, exploratory data analysis, data mining and pattern recognition
• Lead and coordinate key cross-functional data science efforts to accelerate value creation for agile execution team outcome delivery through machine learning
• Use machine learning (ML), deep learning (DL) and other analytical techniques to create scalable solutions for business problems
• Interact with business partners, technologists and engineers to define and understand business problems, and aid them in implementing ML/DL algorithms when appropriate
• Design, develop and evaluate highly innovative models for predictive learning, content ranking, and anomaly detection
• Analyze and extract relevant information from historical data to help automate and optimize key processes
• Work closely with technology, business, and engineering teams to drive model implementations and adoption of new algorithms
• Oversee the health and evolution of agile execution team data science technologies using best practice guidance from the Enterprise Data team
• Articulate the holistic benefits of data science from a business perspective, while maintaining relationships with business analysts, data architects, technical engineers, and project managers
• Meet routinely with the execution team, business stakeholders, and the Director for Data Science, and occasionally with senior Technology leaders and key business partners.

Requirements

• Bachelor's degree in a STEM field; PhD preferred
• 3+ years of professional experience applying quantitative research to optimize human decisions using technologies like machine learning and/or deep learning
• 2+ years of experience using major machine learning/deep learning frameworks (e.g., Scikit-learn, PyTorch, TensorFlow, Keras) and algorithms (e.g., CNN, GAN, LSTM, RNN, XGBOOST)
• 2+ years of data engineering experience with modern big data analytics architectures (Hadoop, SQL, HIVE, Spark, etc.) on major cloud platforms (e.g., AWS, Azure, Google Cloud)
• 2+ years of programming experience in Python
• Working knowledge of modern cloud-based data storage and compute environments (e.g., Snowflake, Databricks in Azure, AI-platform in GCP)
• Experience deploying ML models into discovery/production environments to drive insights using MLOps is a plus
• Experience working in an agile delivery model is a plus
• Demonstrated leadership and self-direction, with a willingness to teach others and learn new techniques
• Excellent communication and presentation skills, with the ability to articulate new and complex ideas to both technical and non-technical partners.

Nice-to-haves

• Experience with deploying ML models into production environments using MLOps
• Experience working in an agile delivery model