As a data scientist and engineer with 7 years of experience developing data-driven solutions in Smart Manufacturing and Data Privacy. Skilled in ML algorithms, MLOps, data governance and pipelines. Awarded Kaggle Silver. I expertise in Agile Methodologies and a keen interest in ESG. I have excellent communication skill and am adept at collaborating effectively with colleagues and stakeholders.
五月 2023 - Present
1. Built manufacturing quality monitoring systems, predictive maintenance solutions, and abnormal detection algorithms for semiconductor advanced packaging, specifically focusing on wire bonding and advanced process control techniques.
1. Implemented efficient data pipelines, ensuring seamless flow for analysis, and developed advanced AI platforms tailored for semiconductor industry needs.
Skills:Time series analysis, MLOps
九月 2022 - 二月 2023
Researched new technology data stack to improve data quality and developed PoC on ELT, data management and governance.
Achievement:
Provided data governance PoC on ETL project by Marquez and Openlineage.
Skills:Data governance, GCP, k8s
十二月 2021 - 八月 2022
Co-worked with domain experts and led the team of 2 in delivering edge-to-cloud predictive maintenance solutions in the solar field.
Achievement:
1. Provided predictive maintenance for 2 PV inverter types in 3 solar fields oversea.
2. Explored time-series log data to find insights that improved traditional maintenance by approximately 5% and increased overall return on investment.
3. Designed monitoring dashboard.
4. Converted PoC code into production code with MLOps.
Skills:scikit-learn, Pandas, Grafana, MLFlow, MinIO, InfluxDB, k8s
三月 2020 - 十二月 2021
Oversaw all aspects of the project, including brainstorming, planning, scheduling, task designation, communication with stakeholders and developers.
Achievement:
1. Led the team of 10 that built end-to-end predictive maintenance engagement platform, which can faster data analysis engagement process, and is used by internal ML projects.
2. Led the team of 5 that built AI Hub platform used by internal ML projects. Help data scientists preserve and share AI Assets with others.
Skills: MLOps, Agile
十月 2019 - 五月 2021
Provided MLOps, data governance solutions in smart manufacturing.
Achievement:
1. Provided a POC report about running Apache MiNiF on Raspberry Pi for collecting data from the edge for ETL projects.
2. Designed system and developed backend search service with CICD pipeline for AI Hub platform.
Skills:RESTful API, NiFi, Apache Atlas, MongoDB, Jenkins, Elasticksearch, Kibana
十月 2016 - 十月 2019
Researched industry trends and developed machine learning models to automate and optimize business processes related to financial and data privacy objectives.
Achievement:
1. Developed financial investment strategies utilizing sentiment analysis for financial institutions, achieving a precision rate of 60% in predicting future market trends. Through backtesting, the strategies yielded a return 10% higher than the market index.
2. Developed a data privacy platform for 7 companies.
3. Created and launched a data marketplace that has facilitated over 5 data science competitions since its inception in 2018.
Skills: NLP, RESTful API, scikit-learn, Pandas, PySpark, Hive, Docker, PostgreSQL
2014 - 2016
2010 - 2014
As a data scientist and engineer with 7 years of experience developing data-driven solutions in Smart Manufacturing and Data Privacy. Skilled in ML algorithms, MLOps, data governance and pipelines. Awarded Kaggle Silver. I expertise in Agile Methodologies and a keen interest in ESG. I have excellent communication skill and am adept at collaborating effectively with colleagues and stakeholders.
五月 2023 - Present
1. Built manufacturing quality monitoring systems, predictive maintenance solutions, and abnormal detection algorithms for semiconductor advanced packaging, specifically focusing on wire bonding and advanced process control techniques.
1. Implemented efficient data pipelines, ensuring seamless flow for analysis, and developed advanced AI platforms tailored for semiconductor industry needs.
Skills:Time series analysis, MLOps
九月 2022 - 二月 2023
Researched new technology data stack to improve data quality and developed PoC on ELT, data management and governance.
Achievement:
Provided data governance PoC on ETL project by Marquez and Openlineage.
Skills:Data governance, GCP, k8s
十二月 2021 - 八月 2022
Co-worked with domain experts and led the team of 2 in delivering edge-to-cloud predictive maintenance solutions in the solar field.
Achievement:
1. Provided predictive maintenance for 2 PV inverter types in 3 solar fields oversea.
2. Explored time-series log data to find insights that improved traditional maintenance by approximately 5% and increased overall return on investment.
3. Designed monitoring dashboard.
4. Converted PoC code into production code with MLOps.
Skills:scikit-learn, Pandas, Grafana, MLFlow, MinIO, InfluxDB, k8s
三月 2020 - 十二月 2021
Oversaw all aspects of the project, including brainstorming, planning, scheduling, task designation, communication with stakeholders and developers.
Achievement:
1. Led the team of 10 that built end-to-end predictive maintenance engagement platform, which can faster data analysis engagement process, and is used by internal ML projects.
2. Led the team of 5 that built AI Hub platform used by internal ML projects. Help data scientists preserve and share AI Assets with others.
Skills: MLOps, Agile
十月 2019 - 五月 2021
Provided MLOps, data governance solutions in smart manufacturing.
Achievement:
1. Provided a POC report about running Apache MiNiF on Raspberry Pi for collecting data from the edge for ETL projects.
2. Designed system and developed backend search service with CICD pipeline for AI Hub platform.
Skills:RESTful API, NiFi, Apache Atlas, MongoDB, Jenkins, Elasticksearch, Kibana
十月 2016 - 十月 2019
Researched industry trends and developed machine learning models to automate and optimize business processes related to financial and data privacy objectives.
Achievement:
1. Developed financial investment strategies utilizing sentiment analysis for financial institutions, achieving a precision rate of 60% in predicting future market trends. Through backtesting, the strategies yielded a return 10% higher than the market index.
2. Developed a data privacy platform for 7 companies.
3. Created and launched a data marketplace that has facilitated over 5 data science competitions since its inception in 2018.
Skills: NLP, RESTful API, scikit-learn, Pandas, PySpark, Hive, Docker, PostgreSQL
2014 - 2016
2010 - 2014