Sydney Data Engineering Meetup

🏠 Location: Ab Initio
🍕 Catering: Ab Initio 😊
💬 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
- 6.40pm: Networking
- 7.10pm: Doors Close

Speakers:
🎤 Stephen Brobst, CTO Ab Initio Software
Talk Title: Data Products Fueled by Generative AI
Talk Summary: Stephen’s specialisation is in the design and construction of data management and AI/ML solutions for Fortune 500 companies. Stephen holds a PhD from MIT’s Computer Science and AI Laboratory and an MBA from Harvard Business School and MIT Sloan. Stephen has dozens of patents and 100+ publications related to ML and advanced data management techniques.
Speaker Bio: Stephen’s specialisation is in the design and construction of data management and AI/ML solutions for Fortune 500 companies. Stephen holds a PhD from MIT’s Computer Science and AI Laboratory and an MBA from Harvard Business School and MIT Sloan. Stephen has dozens of patents and 100+ publications related to ML and advanced data management techniques.

🎤 John Uiterwyk, AI Lead Engineer
Talk Title: Demo: How AI-powered Metadata Creates Context for Enterprise AI
Talk Summary: Why Metadata serves as the best form of Context for AI applications. We will demonstrate how Ab Initio’s unique approach to context and governed metadata powers MCP, agentic planning and multi-agent workflows.
Speaker Bio: John leads the research, prototyping and development of AI systems, focusing on metadata driven data platform agents. John is a software, data and AIML engineer, architect and thought leader, with broad experience across industries including telecoms, finance, digital media, education, sports and government

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: Airtree Ventures
🍕 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
- 6.40pm: Networking
- 7.10pm: Doors Close

Speakers:
🎤 George Jayaratnam, Consultant, MCMC Capital Pty Ltd
Talk Title: Knowledge graphs for code...a winning combination
Talk Summary: Understanding complex codebases can be daunting with numerous interconnected functions, variables, and other dependencies. And that’s even before we get to the data layer. In this talk, we explore how knowledge graphs can offer a powerful way to visualize, navigate, and comprehend unfamiliar codebases more efficiently. Very much in line with the mantra of grounding LLMs with your data (graphRAG), the modular approach taken should enable developers to pick and choose which parts make the most sense given their use case and constraints. Topics covered include knowledge graph basics, a codebase teardown, and time permitting, working with unstructured data (text).
Speaker Bio: George Jayaratnam is an independent consultant working predominantly in the field of quantitative risk management. As someone who often walks up and down the stack, you will also find him in the world of data engineering and application development.

🎤 Jeremy Caine, Technology Strategy and Solution Leader, IBM
🎤 Erol Gurcinar, Technology Strategy and Solution Leader, IBM
Talk Title: Building Graph RAG with advanced data ingestion and scalable hybrid graph vector store
Talk Summary: Graph retrieval-augmented generation (RAG) integrates multiple data sources producing more accurate results over traditional vector search. With advanced parsing and interpreting of content and metadata into knowledge graphs we can ensure important information is not lost in semantic embeddings.This session will explore the benefits and capabilities of Graph RAG in AI systems. It will walkthrough an implementation of Graph RAG using the Unstructured Platform and the scalable, hybrid graph and vector store Astra DB.
Speaker Bio: Jeremy Caine is a digital transformation leader who creates technology solutions with organisations as a catalyst for business model innovation. He is expert in complex systems integration, architecture, and engineering for building distributed applications and global scale platforms using hybrid cloud, data, and AI technology.
Erol Gurcinar is a technical account leader who is focused on serving strategic clients as a trusted technical advisor and enterprise architect. He is an expert in complex projects and systems integration within the financial services sector. He leverages his deep technical expertise and leadership skills to understand a client's business challenges, define their technology strategy, and then orchestrate the execution of those strategies (topics such as - Infrastructure-as-Code, GenAI, Data Platforms, and Security).

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: Groq
🍕 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...