The people who build Cursor, vLLM, Hugging Face and NVIDIA's stack are on one stage for two days, with the teams running it where downtime costs real money. Twenty-minute technical sessions. Architectures, numbers, failure modes.
Last year sold out 19 days before the doors. 480 engineers were in the room.
Models built at Google. Open-source tooling from Hugging Face. NVIDIA silicon beneath vLLM and Red Hat infrastructure. Data in a Databricks lakehouse or Supabase Postgres. Vectors and logs in Elastic. Code written in Cursor, merged through GitHub, built and tested on remote-execution infrastructure like NativeLink. Voice through ElevenLabs.
You picked these tools from docs, benchmarks, and changelogs. You debugged them through GitHub issues at 2 a.m. On October 15–16, the people who build and run this stack are in the same room, taking questions.
Next to them: teams running AI where failure costs real money — across aircraft maintenance, mobility, industrial equipment, telecom infrastructure, and software used by businesses at scale.
Twenty-minute technical sessions. Architectures, numbers, and failure modes. What it costs to run, where it broke, and what they would build differently today. If a talk works as an ad, it does not make this stage.
AI Tooling Engineer
Supabase
Senior Software Engineer
GitHub
Head of Software Development
PALFINGER AG
Director of Field Engineering
Databricks
Inference Research Lead
Red Hat
Senior Enterprise Architect
Lufthansa Technik
Chief Technology Officer
Xplor
Co-Founder and Co-CEO
NativeLink
Founding Field Engineer
Cursor
Senior Manager of Software Engineering
Elastic
Former CTO
Pipedrive
DevRel ML Engineer
Hugging Face
Tech Partner
Credo Ventures
AI & Data Tribe Director
Hrvatski TelekomCompanies on this stage
Bring the problem you're stuck on. Someone in this room has already paid for the answer.
Inside the Engineering Stage
These are programme territories, not a published timetable. Session times and speaker pairings will appear only after they are confirmed.
Start where the product becomes intelligent: model behavior, agent orchestration, voice, and open systems.
Speculative Decoding
Building AI Agents — Multi-Agent Systems and Orchestration
What the Model Forgot to Learn
Giving AI a Voice — Building with Real-Time Speech Models
Open-Source AI in Practice
Move beyond the demo: retrieval, owned data, right-sized models, and systems that hold up when failure matters.
RAG in Production — Retrieval Done Right
Lakehouse to LLM — Building AI on Your Own Data
Why Bigger AI Isn't Always Better
AI in Mission-Critical Engineering
Connect enterprise architecture with the AI-native workflows changing how software is planned, built, and maintained.
Enterprise AI — Architecture, Integration, and Scale
From Idea to Production — Building with Supabase
Shipping Faster with GitHub Copilot and AI-Native Workflows
Building Your Own Software Factory with Cursor
Building Software That Builds Itself
Programme proposal
Four additions that close the gap between building impressive demos and operating dependable AI systems.
Failure testing, traces, quality gates, and production feedback loops.
Prompt injection, tool permissions, memory poisoning, and human approval.
MCP, A2A, and the architecture of agents that work across systems.
Latency, quantization, small models, and on-device AI that can actually ship.
15–16 October 2026 · Sarajevo
Elevate your understanding of emerging trends, gain access to exclusive insights and stay at the forefront of innovation by subscribing to our newsletter.
/ Gajev Trg 4, 71000 Sarajevo, BiH
/ E-mail: info@bluminstitut.ai
/ Call: +38733821822
© 2026 Bloomteq. All Rights Reserved.
Privacy Policy
Elevate your understanding of emerging trends, gain access to exclusive insights and stay at the forefront of innovation by subscribing to our newsletter.
/ Gajev Trg 4, 71000 Sarajevo, BiH
/ E-mail: info@bluminstitut.ai
/ Call: +38733821822
© 2026 Bloomteq. All Rights Reserved.
Privacy Policy
Elevate your understanding of emerging trends, gain access to exclusive insights and stay at the forefront of innovation by subscribing to our newsletter.
/ Gajev Trg 4, 71000 Sarajevo, BiH
/ E-mail: info@bluminstitut.ai
© 2026 Bloomteq. All Rights Reserved.
Privacy Policy
