We can organize an interview with Aldin or any of our 25,000 available candidates within 48 hours. How would you like to proceed?
Schedule Interview NowMy name is Hwei Geok N. and I have over 5 years of experience in the tech industry. I specialize in the following technologies: Python, Data Science, Machine Learning, Deep Learning, Predictive Model, etc.. I hold a degree in Bachelor of Science (BS), Master of Science (MS). Some of the notable projects I’ve worked on include: Automated PFAS & Contaminant Detection for Rhine Water Quality, AI-Powered Document Validation for Telecom Compliance, Productized AI Insights Dashboard for Marketing & Donor Analytics, AI-Enhanced XML Validator for Procurement Data, Conversational AI & Analytics API for Hospital Supply Chain, etc.. I am based in Duesseldorf, Germany. I've successfully completed 15 projects while developing at Softaims.
Information integrity and application security are my highest priorities in development. I implement robust validation, encryption, and authorization mechanisms to protect sensitive data and ensure compliance. I am experienced in identifying and mitigating common security vulnerabilities in both new and existing applications.
My work methodology involves rigorous testing—at the unit, integration, and security levels—to guarantee the stability and trustworthiness of the solutions I build. At Softaims, this dedication to security forms the basis for client trust and platform reliability.
I consistently monitor and improve system performance, utilizing metrics to drive optimization efforts. I’m motivated by the challenge of creating ultra-reliable systems that safeguard client assets and user data.
Main technologies
5 years
2 Years
4 Years
1 Year
Potentially possible
SAP
Challenge: Dutch water companies needed to replace manual analysis of complex time-series water quality data, as traditional workflows delayed critical contamination detection. Solution: Built statistical anomaly detection with 4 threshold configs, integrated 40 discharge facilities, created geospatial correlation engine and 385-chemical classification database. Impact: Identified optimal 1.0σ threshold detecting 36 anomalous substances, flagged real PFBS contamination (27,000 ng/l), reduced analysis from days to real-time. Tech: Python • Pandas • NumPy • Geospatial • Time-Series Analysis
Challenge: Manual document checks were slow and error-prone, delaying telecom tower project delivery and risking compliance. Solution: Built containerized FastAPI backend with Celery, PostgreSQL, Redis. Integrated GPT-4 Vision + Claude 3.7 with category-specific prompts and validation rules. Impact: Reduced review time from days to minutes, achieved 100% precision (zero false approvals) and 90.16% rejection accuracy on invalid documents. Tech: FastAPI • Celery • PostgreSQL • Redis • Docker • GPT-4 Vision • Claude 3.7 • LangChain
Challenge: Teams needed actionable insights from survey data on trust/giving behavior but lacked capacity for statistical/AI analysis. Solution: Built modular Python/R tools with Gradio interfaces, Flask APIs for batch processing, combining AI insights with statistical methods. Deployed via HuggingFace and Heroku. Impact: Enabled on-demand analysis, reduced turnaround from days to seconds, delivered visual reports and AI narratives for marketing/fundraising. Tech: Python • R • Flask • Gradio • HuggingFace • Heroku • Docker • OpenAI
Web tool to detect and correct invalid Incoterms and supplier IDs using LLMs Challenge: Procurement teams submitted XML files with incorrect Incoterms/supplier IDs, causing errors and delays. Solution: Built Streamlit web app that validates XMLs against reference lists, uses OpenAI + LangChain to suggest corrections, and enables instant preview/download of fixed files. Impact: Reduced error correction from hours to seconds, minimized manual lookups, and improved supplier coordination with consistent formatting. Tech: Python • Streamlit • OpenAI • LangChain • Docker
Backend system for inventory queries, vendor analytics, and item substitution Challenge: Hospital needed fast supply chain data exploration - inventory tracking, vendor analytics, and item substitutes across siloed systems. Solution: Built Flask API with Firebase Firestore, integrated OpenAI GPT + LangChain for natural language queries, and created endpoints for inventory, analytics, and substitutions. Impact: Enabled real-time supply chain insights, reduced manual reporting, and provided data-backed vendor/item recommendations. Tech: Python • Flask • Firebase • OpenAI • LangChain • Heroku
Bachelor of Science (BS) in Software Engineering with Multimedia
2009-01-01-2013-01-01
Master of Science (MS) in Intelligent Adaptive Systems
2015-01-01-2018-01-01