Looking for a job

Phoebus Smile

@phoebussmile

Data Scientist at Sichuan Chengxinru Education Consulting Co., Ltd. who developed a RAG pipeline for semantic search and PDF question answering.

Singapore

Message

At Changi General Hospital, I developed Python and SQL ETL pipelines for clinical, operational and infection-control data. I automated reporting workflows and used statistical process control and trend analysis to monitor healthcare indicators.

I also built interactive Tableau dashboards and published them through Tableau Server, giving clinical teams and senior stakeholders self-service visibility into KPIs. I prepared monthly Ministry of Health reporting and worked with stakeholders to investigate abnormal movements and validate data.

As a part-time Data Scientist at Sichuan Chengxinru Education Consulting Co., Ltd., I developed machine learning, deep learning and Generative AI solutions. On the LLM PDF Query project, I developed a RAG pipeline with LangChain and vector databases for semantic search and contextual question answering.

Earlier, at Jia Shi Wei Er Technology Co., Ltd., I developed predictive analytics workflows for healthcare datasets, including models that achieved 93.4% accuracy in a lung cancer biomarker analysis. My background also includes nursing at Singapore General Hospital and a Master in Information Management from KU Leuven University.

Experience

Work history, roles, and key accomplishments

Business Analyst

Changi General Hospital

Mar 2025 - Aug 2026 (1 year 5 months)

Developed Python- and SQL-based ETL pipelines for clinical and operational data, automated KPI workflows, and built Tableau dashboards for senior stakeholders. Applied statistical process control and trend analysis to monitor healthcare indicators.

Python SQL ETL Tableau Statistical Process Control R Data Validation Stakeholder Management Business Intelligence

Data Scientist (Part-time)

Sichuan Chengxinru Education Consulting Co., Ltd.

Jun 2024 - Feb 2025 (8 months)

Developed machine learning, deep learning, and Generative AI solutions including RAG pipelines and CNN models. Supported model deployment using cloud and containerization technologies.

Machine Learning Deep Learning Generative AI NLP Computer Vision Python TensorFlow Flask REST APIs Docker CI CD Kubernetes AWS Azure Lang Chain Faiss Cassandra Streamlit

Data Scientist

Jia Shi Wei Er Technology Co., Ltd.

Sep 2023 - Jun 2024 (9 months)

Analyzed large-scale healthcare datasets, developed predictive models, and improved data quality by 25%. Achieved high accuracy in medical prediction projects and collaborated with clients on modeling strategies.

Python R SQL Machine Learning Feature Engineering SMOTE Cross Validation Hyperparameter Tuning Accuracy Recall F1 Score ROC AUC SEER NHANES

Digital Marketing Specialist; Game

Hui Jie Lin

Jun 2022 - Sep 2022 (3 months)

Managed data-driven digital marketing campaigns, increasing engagement, follower growth, and conversion rates. Executed KOL and cross-platform acquisition campaigns and optimized website content and performance.

Digital Marketing Social Media KOL Networking Google Analytics SQL WordPress HTML CSS SEO ROAS

Senior Staff Nurse

Singapore General Hospital

Feb 2020 - Aug 2021 (1 year 6 months)

Supported doctors during procedures, coordinated patient scheduling, and streamlined patient flow using Endo Pro and Queue System, contributing to a 20% reduction in service delays.

Patient Care Clinical Support Scheduling Endo Pro Queue System Operational Efficiency

Staff Nurse

Singapore General Hospital

Sep 2015 - Jan 2020 (4 years 4 months)

Supported doctors during procedures, coordinated patient scheduling, and streamlined patient flow using Endo Pro and Queue System, contributing to a 20% reduction in service delays.

Patient Care Clinical Support Scheduling Endo Pro Queue System Operational Efficiency

Education

Degrees, certifications, and relevant coursework

KU Leuven University

Master, Information Management

2022 - 2023

Activities and societies: Academic Project: Business Failure Prediction - Built a BeautifulSoup web-scraping pipeline to collect 2M+ data points and developed machine learning models. Optimised XGBoost using Optuna, achieving 85% prediction accuracy, a 15% improvement over baseline.

Pursued a Master in Information Management, completing an academic project on business failure prediction using machine learning.