Practical strategies for detecting and mitigating bias in real-world ML deployments, with case studies from healthcare and fintech applications.
Wong Hui Hui
Machine Learning Engineer & AI Solutions Engineer
I build production ML systems that ship, scale, and stay aligned.
About
Crafting AI solutions with responsibility and rigor
Machine learning engineer with 8 years of experience building production systems across Healthcare, FinTech, and E-commerce. I've helped leading healthcare providers, fintech startups, and e-commerce platforms deploy ML solutions that serve millions across Southeast Asia and North America. My work focuses on the intersection of MLOps, responsible AI, and practical impact—ensuring models not only perform but also stay aligned with human values and business goals.
Core Expertise
Tools & Platforms
Techniques
Featured Projects
Real-world applications of ML engineering principles
Medical Imaging Diagnosis System
AI-powered radiology assistant improving diagnostic accuracy by 32%
Real-time Fraud Detection Engine
ML-powered system preventing $12M in fraudulent transactions annually
E-commerce Recommendation Engine
Personalized recommendations boosting conversion by 28%
LLM-Powered Customer Service Bot
RAG system handling 70% of customer inquiries without escalation
Predictive Maintenance System
IoT and ML reducing equipment downtime by 40%
AI Content Moderation Platform
Multi-modal content filtering protecting 10M+ users
Experience
A journey through production ML systems
2022 - Present
Senior ML Engineer
TechCorp Solutions
Led ML infrastructure modernization serving 50M+ daily predictions across healthcare and fintech verticals
2019 - 2022
ML Solutions Engineer
DataDriven Consulting
Delivered 15+ production ML systems for Fortune 500 clients, saving $45M annually through automation
2016 - 2019
Data Scientist
InnovateLabs
Built the company's first ML platform from scratch, pioneering their entry into AI-powered products
Writing & Talks
Sharing insights from the trenches
A comprehensive guide to implementing robust ML pipelines that can handle millions of predictions while maintaining model quality.
Beyond inference costs: exploring the real operational challenges of running large language models in production environments.
Keynote on implementing ethical AI systems in medical diagnostics, focusing on transparency, accountability, and patient safety.
Technical deep-dive into building streaming ML systems that maintain sub-100ms latency at scale, with lessons from fraud detection.
Subscribe to Newsletter
Get practical ML notes, once a month.
Testimonials
What colleagues and clients say
Hui Hui's ability to bridge complex ML theory with practical engineering solutions is exceptional. The fraud detection system she built transformed our risk management capabilities.
CTO, PaySecure
Working with Hui Hui on our medical imaging project was transformative. Her focus on responsible AI and model interpretability helped us gain regulatory approval and build clinician trust.
Chief Medical Officer, Regional Health Network
Hui Hui consistently delivers production-ready ML systems that scale. Her emphasis on monitoring and observability has saved us countless hours in debugging and maintenance.
VP Engineering, ECommerce Giant
The most organized and detail-oriented ML engineer I've worked with. Her documentation and best practices have become the template for our entire team.
Director of Data Science, InnovateLabs
Let's Build Responsibly
Open to consulting, speaking, and collaboration opportunities