Responsibilities
- Data Analysis & Anomaly Detection: Perform exploratory data analysis (EDA) on semiconductor manufacturing data, including wafer fabrication, yield, and defect rates. Identify anomalies and outliers in semiconductor production data, suggesting corrective actions to improve yield.
- Model Development & Feature Engineering: Develop predictive models using machine learning techniques (such as regression, classification, and clustering) to optimize manufacturing processes and improve product quality. Extract relevant features from raw data, considering factors like material properties, process parameters, and environmental conditions.
- Visualization: Create clear and informative visualizations to communicate findings and insights to stakeholders.
- Collaboration: Work closely with engineers and domain experts to understand semiconductor processes and translate business requirements into data-driven solutions
- Continuous Improvement: Stay up to date with industry trends, research advancements, and emerging technologies in data science and semiconductor manufacturing.
Basic qualifications
- Master’s or Ph.D. with a thesis in Engineering, Computer Science, Data Science or related field. Practical experience with Virtual Metrology, AI, process control, yield improvement, quality control, semiconductor process engineering, image analytics, or related semiconductor field focus.
- 3 plus years in semiconductor manufacturing or artificial intelligence.
- Proficient in Python, with strong knowledge of machine learning algorithms and statistical techniques.
- Familiarity with web applications and reporting.
- Experience with SQL and database management.
- Project experience in AGILE, Waterfall, Scrum, Software Development Lifecycle, JIRA, Change management, Release management, and Configuration management.
- ML frameworks:
- Decision trees, Clustering, Regression, Neural Networks, NLP, Pytorch, Big data, Tensorflow, Pandas, Streamlit
- Tools and technologies:
- Docker, Containerization, Kubernetes, Jenkins, Ansible, Elasticsearch, SSL, Microservices, data visualization tools (e.g., Streamlit, Tableau, PowerBI, etc.).
- Cloud expertise:
- Google Cloud Platform, OpenShift Container Platform
- AI Skills:
- AI specialization and Virtual Metrology/Modeling/Computation:
- Python library sklearn, xgboost, pycaret, etc. but the capability to learn any new package is most important.
- Familiar with the general process of data science work like data extraction, feature extraction, feature selection and modeling.
- Familiar with the skills to deal with time series data (feature extraction, modelling, similarity measure of time series).
- Image specialization: Familiar with deep learning network CNN and package keras.
- Frontend:
- Languages: HTML, CSS, JavaScript, Typescript
- Frameworks/Libraries: Angular, HighCharts, Plotly, AG Grid, BootStrap, Ngx Bootstrap, RxJS
- High capability to learn any new package.
- Packaging: npm, Jenkins
- Backend/API:
- Languages: Python
- Frameworks: Flask, FastAPI, Experience with RESTful APIs, Minor experience with WSLs
- Databases: MySQL, MSSQL, Oracle, PostgreSQL, MongoDB, Neo4j, BigQuery SQL, Snowflake SQL, basic understanding of SSL
- Tools:
- Git , Bitbucket
- Ability to conduct and/or attend meetings when needed in the evening.
- Excellent communication skills to collaborate with cross-functional teams.
- Adaptability and willingness to learn new technologies and methodologies.
Preferred qualifications
- Prior experience in semiconductor manufacturing, yield optimization, or process control is highly desirable.
- 5 plus years in semiconductor manufacturing or artificial intelligence focused on yield ramp.
Tags & focus areas
Used for matching and alerts on DevFound Fulltime Data Science Ai