Melbourne Data Engineering Meetup

🏠 Location: Stone & Chalk Melbourne
🍕 Catering: Neo4j 😊
💬 Join our Slack Group here: Data Engineers Slack Channel

Schedule:
- 5.30pm: Doors Open
- 6.00pm: Announcements and Welcome
- 6.10pm: 1st Talk
- 6.40pm: 2nd Talk
- 7.10pm: Networking
- 7.30pm: Doors Close

Speakers:
🎤 Fanghua (Joshua) Yu, Founder, GraphWay
Talk Title: Has RAG Kept Its Promises? Hallucination, factuality, explainability—wins vs gaps
Talk Summary: This is a clear, practical look at RAG in 2025. We’ll talk about what really cuts mistakes, what still goes wrong, and simple ways to make RAG fast, cheap, and reliable. Topics include: better chunking and retrieval, when re-ranking helps, when a knowledge graph is worth it, and where agents or images/tables fit.
Speaker Bio: Fanghua (Joshua) Yu is a graph-first AI builder focused on turning structured data and unstructured documents into trustworthy answers. He leads GraphWay AI, developing document parsing, knowledge extraction, and GraphRAG pipelines that run efficiently on modest GPUs.Joshua writes frequently on Medium, covering RAG architectures, knowledge graphs, and multimodal retrieval, and speaks to practitioners about making GenAI production-ready.With a background in solution design and data platforms, he blends knowledge graphs with LLMs to reduce hallucinations, improve traceability, and drive outcomes for enterprise analytics. He enjoys connecting communities and sharing playbooks for fast, affordable, explainable RAG at real scale.

🎤 Jonathan Carroll, Principal Consultant / Data Scientist / Engineer / Developer, Irregularly Scheduled Programming
Talk Title: Graph Database Projects for Fun and Profit
Talk Summary: Is a Graph Database a good fit for the shape of this particular data? Sometimes it is, sometimes it isn't. In this talk I'll demonstrate three projects I've worked on involving Neo4j databases - one for fun involving an actual "knowledge" graph extracted from my Obsidian notes; one for profit involving identifying opportunities for drug repurposing; and one you might not expect involving maths puzzles.What makes Neo4j a good fit in each of these cases? What does it offer beyond more traditional relational data modelling? What are the challenges involved with getting data in and out of a graph database that need to be considered? I'll aim to answer all of these and hopefully inspire you to add a graph database to your next project.
Speaker Bio: Jonathan Carroll is an independent contractor and principal consultant at Irregularly Scheduled Programming, currently remotely contracting with biotech companies in USA and Europe. He received a PhD in theoretical physics from the University of Adelaide where he programmed mainly in Fortran. He has worked in the South Australian public service in fisheries, programming in R. He has since branched out to polyglot programming in Python, Julia, Rust, Haskell, APL, and a variety of other languages. Jonathan is an editor of the RWeekly (rweekly.org) newsletter, regularly blogs about explorations in programming at jcarroll.com.au and is active on mastodon at fosstodon.org/@jonocarroll

If you'd like to present at future meetups, please submit your talk here!

Remember to bring along some great questions! See you all there...

🏠 Location: Groq
🍕 Catering: Groq 😊
💬 Join our Slack Group here: Data Engineers Slack Channel
Schedule:
- 12.00pm: Doors Open
- 12.30pm: Workshop
- 1.30pm: Q&A/Networking
- 2.00pm: Doors Close
Facilitator
🎤 Hatice Ozen, Head of Developer Relations, Groq
Workshop Title: Build a Real-time Deep Research Agent in One API Call
Workshop Summary: Groq is saying hello world to Australia. Our Sydney datacenter just went live, bringing you low latency inference and this is our inaugural developer workshop down under – we’re here to connect, set you up with credits, and show you what to ship when latency isn’t a constraint anymore.
AI agents today require complex orchestration: managing state, routing tools, handling retries, and coordinating multiple LLM calls, all while fighting latency at every step.
In this hands-on workshop, we’ll build a sophisticated deep research agent in a single API call with zero orchestration code and talk about all things tools and model context protocol (MCP).
Speaker Bio: As Head of Developer Relations at Groq, Hatice empowers developers, startups, and business leaders alike to both understand how to leverage AI and how to build AI applications that leverage real-time inference for a best-in-class user experience.
With a background in community building and application development, she’s passionate about making AI accessible to all, driving innovation across the AI ecosystem.
If you'd like to present at future meetups, please submit your talk here!
Remember to bring along some great questions! See you all there...

🏠 Location: Stone & Chalk Melbourne
🍕 Catering: Groq 😊
💬 Join our Slack Group here: Data Engineers Slack Channel

Schedule:
- 5.30pm: Doors Open
- 6.00pm: Announcements and Welcome
- 6.10pm: 1st Talk
- 6.40pm: 2nd Talk
- 7.10pm: Networking
- 7.30pm: Doors Close

Speakers:
🎤 Hatice Ozen, Head of Developer Relations, Groq
Talk Title: Need for Speed: API Edition
Talk Summary: Introduction to Groq API, why real-time AI inference is crucial to modern day applications, and how to easily port over existing applications to benefit from performance enhancements and cost-effectiveness.
Speaker Bio: As Head of Developer Relations at Groq, Hatice empowers developers, startups, and business leaders alike to both understand how to leverage AI and how to build AI applications that leverage real-time inference for a best-in-class user experience.
With a background in community building and application development, she’s passionate about making AI accessible to all, driving innovation across the AI ecosystem.

🎤 Michael Bazzoli, Forward-Deployed AI/ML Engineer, Groq
Talk Title: Building Real-time Agents with MCP
Talk Summary: Learn how to leverage MCP servers with fast AI inference for powerful agents that can connect your users to external applications and offer a developer experience that doesn’t lag.
Speaker Bio: Michael Bazzoli is an AI/ML Engineer at Groq, where he focuses on forward‑deployed machine‑learning solutions that power real‑time inference at scale. He also serves as a part‑time instructor for Interview Kickstart’s Machine‑Learning Engineering boot‑camp, teaching topics ranging from LLM training and fine‑tuning to modern generative‑AI architectures. His deep expertise spans large language models, generative AI, computer vision, and production‑grade ML system design.

If you'd like to present at future meetups, please submit your talk here!
Remember to bring along some great questions! See you all there...

🏠 Location: Stone & Chalk Melbourne
🍕 Catering: Confluent 😊
💬 Join our Slack Group here: Data Engineers Slack Channel

Schedule:
- 12.00pm: Doors Open
- 12.30pm: Workshop
- 1.30pm: Q&A/Networking
- 2.00pm: Doors Close

Facilitator
🎤 TBC, Confluent
Workshop Title: Unlocking Real-Time, Reliable, and Reusable Data
Workshop Summary: Most organisations are struggling with an incredibly common task - moving your operational data to your analytics estate. Huge effort goes into creating, monitoring, and maintaining data pipelines. The business relies on these pipelines.
But current ETL and ELT processes are brittle. Pipelines break, the same data is processed multiple times, and trust in the data erodes. Organisations spend time and money just keeping these pipelines running, at the expense of building meaningful data products.
Tableflow solves this problem.
Tableflow = Better, Faster, More Trustworthy Data at the Click of a Button
Tableflow helps you unite analytics and operations with data streaming. It converts streaming data to Apache Iceberg® tables for data warehouses, data lakes, and analytics engines.
Confluent’s unified platform, including Kafka, Flink, Stream Governance, and Tableflow for Iceberg and Delta Lake, helps businesses streamline analytics, reduce complexity, and maximise ROI.
The future of data is real-time, governed, and efficient.
Join us for lunch to learn more about Tableflow including a demo.

If you'd like to present at future meetups, please submit your talk here!

Remember to bring along some great questions! See you all there...