AI & Machine Learning
PythonTensorFlowPyTorchNLPComputer VisionLLM Evaluation
Initializing interface...
About me
Full stack engineer & AI researcher
Who I am
I'm an AI Developer and Full Stack Engineer based in Belfast, UK, coming from Kuala Lumpur, Malaysia. With over 3 years of professional experience, I've built production systems that matter—from AI screening pipelines to distributed backend infrastructure handling millions of transactions.
My passion is at the intersection of AI systems and scalable engineering. I don't just build—I solve problems with elegance and measurable impact.
What I build
- →AI & Machine Learning systems with production rigor
- →Distributed backend infrastructure and microservices
- →Full-stack web applications with React and TypeScript
- →Research on LLM evaluation and AI system benchmarking
- →High-performance data processing pipelines
- →Cloud-native applications on Kubernetes and cloud platforms
3+
Years experience
50+
Production systems
$1B+
Transaction volume handled
10x
Avg performance gain
Technical Stack
Core expertise
Balanced engineering spanning AI/ML systems, distributed backend architecture, and modern full-stack development.
Backend & Distributed Systems
JavaSpring BootApache KafkaSQLPerformance TuningSystem Design
Full Stack Development
TypeScriptReactNext.jsAngularAPI DesignProduct Delivery
DevOps & Infrastructure
DockerKubernetesCI/CDObservabilityCloud ServicesScalable Deployment
Continuously learning and exploring emerging technologies in AI, cloud infrastructure, and web performance. Always eager to work on challenges that push boundaries and solve real problems.
Work & Impact
Experience Highlights
Selected projects showcasing AI implementation, distributed systems engineering, and measurable business impact.
AI Screening Pipeline for SEIS/EIS Evaluation
Built an AI-driven screening workflow to evaluate SEIS/EIS company profiles with structured scoring and explainable ranking outputs.
Technologies
PythonNLPData PipelinesModel Evaluation
Impact: Improved analyst throughput while increasing consistency and decision transparency.
Legal Knowledge Management with NLP Recommendations
Developed an AI-powered legal intelligence platform that indexed domain knowledge and recommended relevant references using semantic search.
Technologies
LLMsVector SearchTypeScriptBackend APIs
Impact: Reduced retrieval friction and enabled faster legal insight workflows for knowledge users.
ERP Platform for HR, Sales, and Warehouse Operations
Engineered core ERP modules and integrations to unify operations across departments, with robust role controls and auditability.
Technologies
JavaSpring BootSQLAngular
Impact: Delivered measurable operational efficiency gains including a 40% payroll process time reduction.
Real-Time Logistics and CRM Performance Engineering
Implemented real-time data flows and optimized backend processing paths for logistics and CRM workloads under sustained traffic.
Technologies
Apache KafkaDistributed SystemsObservabilityAPI Optimization
Impact: Achieved 10x query latency improvements and supported 5000+ processed messages per hour.
Research & Publications
Contributions to the field
Published research on temporal reasoning in LLMs, vision-language models, and human action recognition. Focused on understanding AI system limitations and improving benchmark design.
LLM EvaluationTemporal ReasoningBenchmark Design
DateLogicQA: Benchmarking Temporal Biases in Large Language Models
Benchmarking Temporal Biases in Large Language Models
Designed a benchmark focused on temporal reasoning failure modes in LLM systems and analyzed behavior under structured evaluation settings.
Read publication
Computer VisionVision TransformersCNNsAction Recognition
Language as a Label: Zero-Shot Multimodal Classification of Everyday Postures under Data Scarcity
Evaluating Vision Transformers and CNNs for Human Action Recognition
Investigates how the specificity of natural language prompts influences zero-shot classification performance in modern vision language models (VLMs) under severe data scarcity.
Read publication
Exploring AI evaluation, benchmarking methodologies, and real-world applications of machine learning systems.
View all researchLet's talk
I'm always interested in exploring new opportunities, collaborating on interesting problems, and discussing ideas. Whether it's a project, a question, or just to say hi, feel free to reach out.
Let's build something impactful together
business@mingzetang.dev
Connect
GitHub
github.com/tangmz
Connect
linkedin.com/in/ming-ze-tang
Connect
Medium
medium.com/@mztang0428
Connect
I read and respond to every message. Looking forward to connecting.