Coffee With Developers Aug 31, 2026

AI Vector Search at Scale - Ewa Szyszka - Ewa Szyszka

Ewa Szyszka

Ewa Szyszka argues the strongest AI founders combine technical fluency with deep domain expertise. Learn to scale vector search, slash LLM costs, and deploy robust agentic evaluations.

Pause
Mute Enter Fullscreen
#1 about 2 min

Optimizing token usage with vector search retrieval

Efficient information retrieval using vector databases prevents hitting rate limits and reduces token costs.

#2 about 2 min

Preparing and chunking data for vector databases

Understanding use cases and properly chunking data before embedding ensures highly relevant search results.

#3 about 2 min

Scaling search and managing multimodal data types

Vector databases handle large-scale multimodal data like audio and video using algorithms like HNSW and TurboQuant.

#4 about 2 min

Bridging customer needs and technical solutions in developer relations

Developer relations engineers build practical workshops based on real-world customer stories and ecosystem demands.

#5 about 2 min

Exploring multimodal AI applications beyond standard language models

Processing unstructured data like CCTV footage and audio opens new possibilities for anomaly detection and advanced analytics.

#6 about 2 min

Managing dirty data and continuous agentic evaluations

Implementing continuous evaluation processes with golden answer datasets is critical for handling real-world data errors in production.

#7 about 2 min

Comparing startup founder experiences with developer relations roles

Building in public as a founder or advocate sharpens technical skills and fosters rapid continuous learning.

#8 about 3 min

Combining domain expertise with technical skills for AI startups

Founding successful AI companies requires pairing technical fluency with deep domain knowledge and delegating specialized tasks.

Matching moments

5:23 min

Evaluating venture capital value and AI sustainability

Frank Seehaus Frank Seehaus +3 · World Congress 2026 Europe

6:31 min

Evolving venture capital strategies amid artificial intelligence democratization

Christian Nagel Christian Nagel +3 · World Congress 2026 Europe

3:00 min

Introduction to generative AI and vector search

Mary Grygleski Mary Grygleski · LIVE

8:55 min

Audience questions on data integration and future action models

Vijay Krishan Gupta +1 · LIVE

1:31 min

Essential AI and human skills for future teams

Alexander Weißhaupt Alexander Weißhaupt +1 · World Congress 2025

4:09 min

Dismantling AI hype and focusing on practical use cases

Rudi Bauer Rudi Bauer +1 · Cappuccino with HR

Upcoming sessions on this topic

Open session

World Congress 2026 North America

What AI Startups Are VCs Actually Funding in 2026

Mariane Bekker

​Mariane Bekker, Head of Developer Relations at You.com; Founder at Founders Bay

Mariane Bekker
Open session

World Congress 2026 North America

Building the AI Era Through Developer Communities: A Competitive Advantage for Engineers & Teams

John Komarnicki

National Executive Advisor at Code & Coffee | Engineering & AI Community Leader

John Komarnicki
Open session

World Congress 2026 North America

Edge AI: Running Agentic Intelligence Where Internet Can't Reach

Nitin Eusebius

AWS - Principal Solutions Architect

Nitin Eusebius
Open session

World Congress 2026 North America

Engineering the Pivot: How Creative Strategy Solves the Hard Problems of AI Accuracy and Scale

Shruti Tiwari

AI/ML product manager, Dell

Shruti Tiwari
Open session

World Congress 2026 North America

Making Science Larger, not just Faster

Yuval Dvir

Commercial Executive, SandboxAQ

Yuval Dvir
Open session

World Congress 2026 North America

The Five Percent Club: The Culture and Technological Shift Behind Successful AI Deployments

Tara Hernandez

Tara Hernandez, VP of Developer Productivity at MongoDB

Tara Hernandez