# Esther S.

> Machine Learning Engineer

Location: San Francisco Bay Area, United States
Profile: https://flows.cv/esthers

- Extensive analytics and engineering experience across tech, startups, research institutions, consulting, and insurance industries
- Proficient in big data processing and end-to-end deep learning systems at scale
- Hands-on expertise in generative AI, computer vision (object tracking), natural language processing (search), and reinforcement learning recommendation (content-based personalization)
- Skilled in scientific computing languages and deployment tools for scalable AI and data solutions

Programming Languages: Python, Scala, R, Java, VB, Matlab, C
Web stacks: HTML, CSS, JavaScript
Frameworks: Django, Flask, Falcon
Deployment & Cloud: AWS, GCP, Azure, Docker
Database: MYSQL, MongoDB
Dashboard & Visualization: Tableau, Plotly, Shiny, Dash
Big Data: Spark, Hadoop
Machine learning: TensorFlow, Keras, scikit-learn
Workflow & Orchestration: Airflow, OpenConnect

Others:
- SOA certified associate actuary(ASA)(2015), pursuing FSA quantitative finance and investment track (paused due to career path change)
- SFI certified Advanced Securities Specialist and Securities Investment Analyst (2012)
- TABF certified Derivatives Specialist (2012)

## Work Experience
### Software Engineer, AI @ LinkedIn
Jan 2021 – Present | Sunnyvale, California, United States
Premium: acquisition and retention

Graph Affinity: drive network engagement by generating affinity signals

Tools: Spark, Scala, Python, Java, Azkaban, Tensorflow, A/B testing, Airflow

### Data Scientist @ ByteDance
Jan 2021 – Jan 2021 | Mountain View, California, United States
• Designed and built the 1st generation analytical web app for real-time insights and visualizations in public relations.
• Conducted text mining, sentiment analysis, and topic classification for media trends.
• Developed ETL pipeline to stream metadata from social media platforms.

### Data Scientist, Machine Learning @ BCG X
Jan 2019 – Jan 2021 | Manhattan Beach, California, United States
•Geofencing Security System(CV): object detection/tracking (RetinaNet, optical flow)
•Credit Risk Forecasting: credit limit and default rate forecasting
•Knowledge Search System(CV + NLP): optical character recognition(OCR), question-answering, machine reading comprehension(MRC), learning to rank(LTR), multi-label classification
•Personalization App(Reinforcement learning): Thompson sampling for the cold-start problem recommendation
•Other POC ML & Eng projects: data augmentation(imputation, web-scraping), automatic reporting and dashboarding, real-time tracking system(IoT in healthcare)

* Algorithms: BERT, logistics regression, GRU, CNN, RNN, stacking, BiDAF, kNN, decision tree
* Packages: numpy, pandas, scipy, opencv, sklearn, skmultilearn, spacy, allennlp, elasticsearch, asyncio
* Industries: manufacturing, finance, retailer, pharmaceutical, nonprofit
* Tech stacks: Python, PostgreSQL, MongoDB, Spark, VBA, Tableau, Plotly(html, dash)
* Tools: Azure, GCP(Kubernetes, BigQuery, DataStudio, Firestore), AWS(S3, EC2, EMR, Sagemaker)

### Statistics Tutor @ University of California, Berkeley
Jan 2017 – Jan 2018
Fall 2017: Stat 2 and 20
Fall 2018: Stat 2, 20, 133, 134 and 135

- Introduction to statistical and critical thinking
- Introduction to Probability and Statistics
- An introduction to computational data analysis

### Statistical Consultant (co-op) @ University of California, Berkeley
Jan 2017 – Jan 2017 | Berkeley, California, United States
Tech Stack: R (tidyverse, metafor, psych, mediation)

Methods: Mediation analysis, Wilcoxon signed-rank test, Meta-analysis

Domains: Psychology, Social Science, Pharmaceutical and Drug-Medication Research

Project Highlights:

- Resolved multicollinearity issues in mediation analysis to enhance model validity and interpretability.
- Recommended and applied nonparametric Wilcoxon testing for evaluating Compassion Cultivation Training Questionnaire responses, addressing non-normality in the data.
- Supported medical research by conducting meta-analyses, including effect size estimation, heterogeneity testing, and synthesis of results using established R packages.

### Data Scientist Intern @ BCG X
Jan 2018 – Jan 2018 | Bellevue, Washington, United States
• Developed predictive models to forecast weekly crop harvest and amount of fruit loads on the plants
• Predicted greenhouse water levels and dried rates with LSTM, dynamic regression, and threshold autoregression
• Implemented grey models to provide an alternative solution for new clients without enough data


* Tech stack: Python, R, Falcon, Keras
* Algorithms: Gradient Boosting, Random Forest, LSTM, ARIMA, Fourier Transform, Dynamic Regression 
* Industry: Agriculture

### Data Scientist Intern (co-op) @ Intento, Inc.
Jan 2018 – Jan 2018 | Berkeley, California, United States
Designed a customer‐facing sentiment APIs comparison experiment to distill customer satisfaction for recommendation

* Tech stack: Python, Rest-API(Flask)

### Researcher, Disease Surveillance And Risk Monitoring (DiSARM) Platform @ UCSF Medical Center
Jan 2018 – Jan 2018 | San Francisco, California, United States
• Classified building types in Africa with OpenStreetMap to implement malaria control into the household level.
• Combined Leaflet and Shiny to visualize the classification model into a web app to deliver insights at scale


## Education
### Master's degree in Statistics
University of California, Berkeley

### Information System Training Program in Computer Science and Information Engineering
National Taiwan University

### Bachelor's degree in Statistics
National Taipei University


## Contact & Social
- LinkedIn: https://linkedin.com/in/esther-ksu

---
Source: https://flows.cv/esthers
JSON Resume: https://flows.cv/esthers/resume.json
Last updated: 2026-03-29