As a Data Science Engineer at Micron, you will employ techniques and theories drawn from areas of mathematics, statistics, semiconductor physics, materials science, and information technology to uncover patterns in data from which predictive models, actionable insights, and solutions can be developed.

You will interact with experienced Data Scientists, Data Engineers, Business Areas Engineers, and UX teams to identify questions and issues for data analysis projects and improvement of existing tools. In this position, you will help develop software programs, algorithms and/or automated processes to cleanse, integrate, and evaluate large datasets from multiple disparate sources. There will be significant opportunities to perform exploratory and noval solution development activities.

In this role you will have the following responsibilities:

• Strong desire to grow a career as a Data Scientist in highly automated industrial manufacturing doing analysis and machine learning on terabytes and petabytes of diverse datasets and to deliver meaningful end-to-end solutions for users.
• Experience in the areas: statistical modeling, feature extraction and analysis, supervised/unsupervised/semi-supervised learning. Exposure to the semiconductor industry is a plus but not a requirement.
• Ability to extract data from different databases via SQL and other query languages and applying data cleansing, outlier identification, and missing data techniques.
• Coordinate production deployment activities, including cross-functional communications, approval and execution of changes in live environments.
• Strong software development skills.
• Strong verbal and written communication skills.

Required Qualifications

• Bachelor or Master degree in Computer Science, Computer Engineering, Business Analytics, Data Science or AI.

Or

• Equivalently, minimum 2 years of practical experience in development of scalable and stable AI applications.

Required Technical Experience

• Minimum 1 year of Semiconductor process, process control or manufacturing data analysis on-job experience in a high-volume manufacturing (HVM) environment is a must. Semiconductor processes are photolithography, etch, deposition, CMP, diffusion, die saw, grinding, etc. Semiconductor process control experience include statistical process control (SPC), Run-to-run (R2R), design of experiments (DOE), and semiconductor manufacturing process root cause analysis (RCA) etc.
• Strong programming skills in Python and/or R
• Proficiency in machine learning and advanced analytical methods
• Experience with deep learning frameworks such as TensorFlow, PyTorch, or similar
• Familiarity with front-end and visualization tools like JavaScript, AngularJS 2.0, R Shiny or Streamlit.

Required Soft-skill Experience

• Strong analytical and problem-solving skills with a data-driven mindset.
• Effective communication skills for cross-functional collaboration with engineering, operations, and quality teams.
• Ability to work independently and manage multiple priorities in a fast-paced environment.
• Detail-oriented with a commitment to quality and continuous improvement.
• Adaptability and resilience in a dynamic manufacturing setting.

Preferred Experience or Willingness to Learn

• Distributed computing frameworks: PySpark, SparkR, or SparklyR
• Big data technologies: Hadoop, Hive, Spark, HBase
• Working knowledge of Teradata or other SQL-based databases
• Exposure to ETL tools like SSIS, containerization with Docker, and cloud platforms such as Google Cloud Platform (GCP)
• Knowledge of equipment troubleshooting and preventive maintenance procedures.
• Experience with advanced node technologies (e.g., 5nm, 3nm) or 3D NAND/DRAM processes.

Nice-to-Have Skills

• Experience handling time-series data, image data, semi-supervised learning, or non-stationary data distributions
• Familiarity with Manufacturing Execution Systems (MES)
• Contributions to top-tier conferences such as CVPR, NeurIPS, ICML, or KDD (Note: This is not a research-focused role)

Designs, develops and programs methods, processes, and systems to consolidate and analyze unstructured, diverse "big data" sources to generate actionable insights and solutions for client services and product enhancement. Interacts with product and service teams to identify questions and issues for data analysis and experiments. Develops and codes software programs, algorithms and automated processes to cleanse, integrate and evaluate large datasets from multiple disparate sources. Identifies meaningful insights from large data and metadata sources; interprets and communicates insights and findings from analysis and experiments to product, service, and business managers.