Data Scientist

Key Skills

Java Programming, Python Programming, SQL, Git, JIRA, SPARK Programming

Job Description

Samsung Austin Semiconductor is one of the most advanced semiconductor manufacturing facilities in the world with more than 3,000 employees and 2.45 million square feet of floor space. Samsung Austin Semiconductor has broad semiconductor process technology offerings serving customers in various application areas including mobile, consumer, networking/high performance computing, Internet of Things, RF and automotive.

Since 1996, its parent company, Samsung Electronics Co., Ltd has invested approximately $17 billion in Samsung Austin Semiconductor’s Austin, Texas campus, making it one of the largest direct foreign investments in United States history. Samsung Austin Semiconductor is a premier employer who provides a great place to work, as well as advanced and upskilled training to thriving employees. Visit www.samsung.com/us/sas.

Samsung Austin Semiconductor strives to be the World's Best Foundry.

As a Data Scientist at SAS, you will be involved in the entire lifecycle of projects that help improve factory outcomes such as yield, output, and cost reduction. The Data Science team is responsible for building large-scale analysis programs that derive business insights from extremely complex data sources, as well as implementing solutions based on those insights. Working with an experienced team will provide access to a wide range of knowledge in areas such as data analysis, semiconductor manufacturing, and process optimization. The ideal candidate has a strong coding and statistical background as well as hands on experience implementing solutions that utilize the full data science cycle including data extraction, cleaning, exploration, and machine learning.

Role and Responsibilities

• Develop programs utilizing data science tools such as Python and Spark to analyze billions of records of data.
• Work collaboratively with team members to design programs for fault detection, predictive analytics, and root-cause analysis.
• Perform data analysis throughout the program creation lifetime to ensure data validity and integrity, such filtering extreme outliers, normalizing data, etc.
• Utilize data mining, feature engineering, machine learning, and statistical analysis to make new discoveries within various data sources.
• Condense complex problems and solutions for presentation to relevant teams.
• Workdays & Hours: M-F, 1st Shift, 8 AM to 5 PM.

Skills and Qualifications

Education, Training, Certification(s) and Minimum # Years Required:

• Bachelor’s Degree in “STEM” field (Science, Technology, Engineering, Mathematics or Data Science). Masters preferred.
• Minimum 3 years of experience in Data Science or semiconductor manufacturing.

Knowledge, Skills, Abilities, Software, Tools: List MOST important requirements first. Then list soft skills and desired (but not required), experience.

• Proficiency in Python, Spark and SQL.
• Solid background in statistics (hypothesis testing, outlier filtering, normalization).
• Familiarity with machine learning including model training, validation, and feature reduction techniques.
• Hands on experience with supervised learning algorithms such as linear regression, tree based models, and neural networks.
• Ability to work effectively with subject matter experts to ensure data is analyzed properly.
• Experience in software development toolkits (Jira and Git).
• Agile/Scrum development experience.
• Willingness to learn the intricacies that come with semiconductor data.

Why You’ll Enjoy Working Here:

• Interaction with leading-edge tech manufacturing that produces TBs of data daily.
• Collaboration with a small, highly motivated team to develop and implement new ideas.
• Bonus incentive programs.
• Great Benefits (employer matched 401k, medical, dental, extensive PTO).
• Amenities (soccer field, 2 gyms, full court basketball / tennis courts, Frisbee golf, walking trails).
• Subsidized lunches.
• Flexible work schedule