yieldWerx is an end-to-end Semiconductor Test data analytics solutions company, A global company with headquarters in Texas, USA & and offices in Pakistan, & and the Philippines.
We are seeking to engage with a senior level Data Scientist, as a long-term consultant, with a proven track record in statistical and machine learning analysis (experience in the semiconductor, electronics, and automotive industries would be a huge advantage).
This role requires proficiency in data visualization, process optimization, and staying abreast of emerging technologies in the field of data science. Selected candidates will work with other members of Global Yield org including Process Integration, Device and defect engineering teams, fab module/yield teams, and TD team members to achieve yield ramp-up and process optimization in the early production stage, supporting internal and external customers.
a. Technical Expertise:
•Proficient in implementing supervised & and unsupervised machine learning techniques, conducting analysis of variance (ANOVA), & and performing statistical significance tests.
•Create and optimize Data Cleaning Pipelines using Natural Language Processing (NLP).
•Build Vector Database Pipelines from scratch, managing a vast dataset of large text records.
•Engineer Large Language Model Prompts for data fed from Vector Database Search.
•Utilize a diverse tech stack including Python, Linux, Docker, SSH, AWS, Pytorch, Spacy, NLTK, Weaviate, and AWS Bedrock.
•Identify valuable data sources and set automated data collection process to build and manage the dataset used for yield analysis.
•Work with the Yield Modelling team to develop new yield analysis methods and algorithms to deliver world-class yield analytics & and machine-learning solutions in a high-volume manufacturing environment.
•Develop models & and algorithms to improve and automate process control minimizing yield loss associated with tight process windows.
•Engineering support for technical interactions with internal and external customers.
b. Machine Learning & AI Projects:
•Lead AI/ML projects to enhance process & and product quality for international semiconductor and electronic customers.
•Develop AI/ML frameworks in a Big Data environment.
•Demonstrated capability in creating interpretable models & and deploying advanced algorithms in production environments.
•Hands-on experience in developing & and implementing analytic solutions in Amazon or Azure cloud, leveraging various database types.
•Implement solutions such as Computer Vision for defect detection and test/Inspection efficiency improvement.
c. Data Processing & Analysis:
•Process large volumes of parametric and test equipment data using SQL, Vertica, JavaScript, R data, and Table.
•Derive process metrics correlating to field failure of automobile parts through the analysis of solder manufacturing trace data.
•Create yield visualizations for HBM memory using SQL, and Pandas.
•Expertise in designing and implementing data pipelines for analytical model consumption across structured, semi-structured, and/or unstructured data in batch and real-time scenarios.
•Familiarity with APIs and web services for streamlined data processing and analysis.
d. Big Data Infrastructure & Optimization:
•Integrate semiconductor data into big data extension systems for YMS & FDC.
•Utilize SQL, Python, and Scala for data analysis, data mining, and statistical algorithm implementation.
Required Skill Sets:
•Strong proficiency in data visualization tools such as Tableau, Power BI, or Spotfire.
•Proficiency in employing statistical methods and analytical tools
•Expertise in developing deep learning models for complex problem-solving.
•Familiarity with database optimization, including Cassandra and Oracle.
•Practical experience in working with databases, including SQL, NoSQL, & and Big Data technologies.
•Proven track record of leveraging deep learning techniques to enhance predictive modeling and data analysis.
•Statistical tools such as R, SPLUS, and SAS for advanced statistical modeling.
•Experience with Big Data tech, including Spark, Hadoop, and related frameworks.
•Hands-on experience with tools and technologies specific to semiconductor and electronics industries, including ATE, SIMS, FA, UHV, High-Voltage, Particle Accelerators, and AWS Bedrock.
•Advanced proficiency in Python, programming language, TensorFlow with .Net Integration & Keras, with a focus on data manipulation, analysis, and modeling. Practical expertise in using Python libraries, including Pandas, NumPy, and Scikit-learn.
•Demonstrated proficiency in ETL processes, ensuring seamless extraction, transformation, and loading of data. Experience in designing and implementing robust ETL pipelines for data integration.
•Extensive experience in statistical modeling, including hypothesis testing, regression analysis, & and predictive modeling. Ability to apply statistical methodologies to derive meaningful conclusions from data.
This job is already closed and no longer accepting applicants, sorry.
