About
I'm an Australia-based Lead Data Engineer, AI Engineer, and Data Architect with a PhD in Computer Science and 10+ years of experience designing modern data platforms and analytics systems across finance, healthcare, telecom, utilities, and insurance.
Recently, I've been building production AI systems — including LLM evaluation frameworks, multi-cloud RAG pipelines, and agentic AI workflows — while continuing to work across cloud architecture, data engineering, and platform design.
I'm particularly interested in making AI systems measurable, observable, and reliable in production environments — not just impressive in demos. I enjoy building systems that are scalable, practical, and grounded in real-world constraints.
Outside of engineering, I play music and compose songs — it's how I decompress from the complexity of systems work.
This site is where I share technical writing, side projects, and occasional posts in Vietnamese on topics beyond data and technology.
What I Do
I work across the full data and AI stack — designing enterprise data platforms, building cloud-native pipelines with dbt, Airflow, and Spark, and productionising AI systems that go beyond demos into measurable, observable workflows.
My platform work spans AWS, Azure, GCP, Snowflake, and Databricks. My AI work focuses on RAG systems, LLM evaluation frameworks, and agentic workflows — built with the same engineering rigour as production data infrastructure.
Recent Experience
-
Lead Data Engineer & AI Engineer — SData 2019 – Present
Founder of a boutique AI and data engineering consultancy, delivering cloud-native data platforms, ML solutions, and Generative AI systems for Australian enterprises. Recent work includes multi-cloud serverless RAG across AWS, Azure, and GCP; LLM agent evaluation frameworks using LangGraph and Snowflake; and production RAG pipelines with pgvector and the Claude API.
-
Lead Data Engineer — AustralianUnity Aug 2024 – Mar 2026
Led a team of 8 engineers delivering a HomeHealth reporting solution on AWS. Designed enterprise data models and end-to-end pipelines integrating D365, SFHC, and legacy systems.
-
Senior Data & ML Engineer — Bank of Queensland Apr – Oct 2023
Built ML models for customer segmentation and abusive language detection, productionised via Databricks and Azure ML. Delivered data streaming pipelines for the OpenBanking project using Medallion architecture, PySpark, and Azure EventHub.
Other contracts include CultureAmp, Mobiquity APAC, Macquarie Group, EnergyAustralia, AEMO, Bupa, Telstra, and more — 10+ years of contract engineering across Australia.
Education
- PhD in Computer Science — La Trobe University, Melbourne (2014)
Thesis: Parallel algorithms for the enumeration of combinatorial objects - Master of Computer Science — Ho Chi Minh University of Technology
- Bachelor of Computer Science — Ho Chi Minh University of Technology
Patents & Recognition
- Patent: "Method to Decode Data and Computing Apparatus Using the Same" (2015)
- Award: Group Executive Award, Telstra Q2 2017/18
- Published research in high-performance computing and data algorithms
Tech Stack
Cloud & Platforms
AWS · Azure · GCP · Snowflake · Databricks · Microsoft Fabric
Data Engineering
dbt · Airflow · Spark · AWS Glue · Azure Data Factory · Terraform
AI & ML
LangGraph · Amazon Bedrock · Azure AI Foundry · Vertex AI · pgvector · OpenSearch Serverless · PyTorch
Languages
Python · SQL · Scala · R