Data Scientist - Product Quality Predictive Solutions

About the role

Micron is hiring a Data Scientist in its Fab 10A site to build and productionize machine learning models that support predictive and prescriptive analytics across semiconductor test and manufacturing processes. The role also covers agentic AI and LLM development, including multi-agent systems, retrieval-augmented generation pipelines and tool-using capabilities.

Key responsibilities

• Build and productionize classification and regression models for predictive and prescriptive analytics in semiconductor test and manufacturing.
• Help design and implement multi-agent systems for product quality workflows, including code generation, automated troubleshooting and process optimization.
• Work with RAG pipelines: identify data sources, develop retrieval strategies and improve context quality for LLM-based applications.
• Assist in implementing tool-using capabilities, function calling and agent memory systems.
• Develop maintainable code and analytical pipelines optimized for performance, latency and token efficiency in high-volume manufacturing environments.
• Collaborate with senior team members on testing, deployment and monitoring.
• Communicate analytical insights, model behavior and results clearly to technical and non-technical stakeholders.

Required profile

• Bachelor's degree in Computer Science, Data Science, Operations Research, Mathematics or equivalent.
• Strong desire to grow a career as a Data Scientist in advanced, highly automated industrial manufacturing.
• Coworking experience with cross-functional teams such as solution architects, data engineers and machine learning engineers, or equivalent.
• Ability to explain complex analytical results clearly and to use AI-enabled tools responsibly and effectively.

Required skills

• Proficiency in Python for data analysis and modeling.
• Solid foundation in statistics and/or machine learning (supervised and unsupervised learning, model evaluation, feature engineering).
• SQL for data extraction and manipulation.
• Version control with Git.
• Familiarity with interactive data applications or dashboards (e.g., Streamlit, PowerBI).