PyData Tel Aviv

Join Us for PyData Meetup @ Melio!

Get ready for insightful sessions, networking with the PyData community, and, of course, pizza and beer!
A big thanks to Melio for hosting us and supporting the community.

📅 Details
Date: Sunday, June 14th, 2026
Time: 18:00 - 21:00
Location: Melio Office, Hagag Towers, North Tower, Floor 32, HaArba’a St 28, Tel Aviv
Language: This meetup will be held in Hebrew

🕒 Agenda
18:00: Gathering, snacks, and drinks 🍕🍻
18:30: Welcome words
18:45: Cost-Efficient AI Systems in Practice, Michael Levinger, Senior AI Engineer @ Melio
19:15: Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb, Dr. Adi Sarid, CEO @ Sarid Research
19:45: A Match Made in Heaven: LLM Judgment at Vector-Search Speed, Shon Mendelson, Staff AI Scientist @ Intuit

🎤 Featured Sessions
Cost-Efficient AI Systems in Practice
Speaker: Michael Levinger, Senior AI Engineer @ Melio
Deploying large language models and AI agents in real-world systems requires a constant trade-off between cost, latency, and performance. This talk explores how to optimize LLM- and agent-based systems using techniques such as caching, model routing/cascades, tuning, RAG, and distillation—significantly reducing costs without sacrificing quality. Through a case study of an ATO-agent system, we’ll also cover practical approaches to cost estimation, monitoring, and budgeting.
In addition, we’ll compare leading industry models—such as Gemini, Claude, and GPT—focusing on differences in response speed, cost efficiency, and real-world performance, and how to choose the right model for each use case within broader agentic workflows.

Dr. Data: How We Learned to Stop Worrying and Love the AI Bomb
Speaker: Dr. Adi Sarid, CEO @ Sarid Research
When GenAI dropped, our quant market research agency had a beautifully naive thought: "We can finally replace all our human labelers with a simple API call!" Spoiler alert: Scaling AI without hallucinations isn't quite that simple.
Join us for a brutally honest, technical look at our data science team's journey from prompt-panic to AI-powered productivity. We’ll share our biggest wins and hardest lessons regarding evaluation frameworks, the rapid obsolescence of custom packages, and the newfound "full-stack audacity" of modern data scientists.

A Match Made in Heaven: LLM Judgment at Vector-Search Speed
Speaker: Shon Mendelson, Staff AI Scientist @ Intuit
Last year, I spent far too long chasing a stubborn data quirk: why our system couldn't see that “The Law Offices of John Miller” and “Miller, John S. PLLC” were the same entity. It led to a bigger question: can you achieve LLM-level judgment at vector-search speeds? Traditional vector search is fast, but often misses subtle context like this, while relying entirely on LLMs is too slow and costly for production at scale.
In this talk, I’ll share how we bridged that gap at Intuit with a hybrid system that combines fast vector search, efficient small transformer-based models, and fine-tuned SLMs. The result is a system capable of handling millions of weekly entity comparisons, significantly boosting recall while maintaining precision levels comparable to traditional methods.

🚀 RSVP
Space is limited – RSVP now to secure your spot!
We look forward to seeing you there!