On September 23, we’re bringing the AI community together for an offline Data Science UA meetup — think of it as a back-to-school event, but in the best way possible.
The program will include in-depth work with LLMs, prompt optimization, and new approaches to video content analysis powered by AI agents.
This time, we’ve invited three experts who will share practical, hands-on insights for AI engineers:
👉 Oleksii Shaldenko and Kostiantyn Zdor – Co-founders at Wantent
“The future of content analysis: AI agents, synthetic audiences, and video attributes for deep audience understanding”
Oleksii Shaldenko is the CEO of the Ukrainian AI startup Wantent, which builds AI-powered solutions for evaluating content effectiveness.
He holds a Ph.D. in Engineering and has 8+ years of experience in VFX, including work on top-tier AAA+ Hollywood productions.
Kostiantyn Zdor is the Head of the AI department at Wantent, developing solutions for video analysis. His expertise includes emotional analysis, content success prediction, and applying AI agents and synthetic audiences to model and study viewer interactions.
In their talk, experts will cover:
– What AI-driven approaches to video content analysis are there?
– How can AI agents simulate audience behavior and reactions, delivering fast, scalable insights?
– How to create and utilize synthetic audiences?
– What does in-depth analysis of content attributes (such as pace, color palette, emotional tone of scenes, and context) involve, and how does it enable more accurate predictions of engagement and content perception?
👉 Maksym Kmet – Senior AI Engineer at MacPaw
“A prompt is just the start: A practical guide to LLM control and evaluation”
Maksym Kmet is an AI engineer with 6 years of experience building ML solutions across domains ranging from smart city technologies to recommender systems and NLP. He is currently developing AI solutions tightly integrated with Apple products.
The speaker will share practical insights on:
– How language models generate the next token
– How decoding strategies (top-k, top-p, temperature) shape the output
– How to design effective prompts
– How to evaluate responses using classical metrics and the “LLM-as-a-judge” approach
– How to improve generation quality through automated prompt optimization
This meetup is a must-attend for AI engineers, data scientists, product managers, developers, and anyone eager to understand how today’s AI approaches really work.
Aleksandra Boguslavskaya, CEO & Founder of Data Science UA will moderate the event.
📌 Event details:
🔸 Date & time: Tuesday, September 23 at 18:00 (UTC+3)
🔸 Location: BC Gulliver, Creative Quarter, Tower B, 12th floor
🔸 Address: Palace of Sports metro station, Sportyvna Square 1a, 01023
🔸 Language: Ukrainian
🔸 Price: 790 UAH – standard; 250 UAH – for military personnel; 450 UAH – event recording
🔸 Get your ticket here: http://bit.ly/41EUc4S
