Architecting for Scale: Observability and Search at Extreme Volumes

We're back on January 13th for our first meetup of 2026. Hope everyone had a great Christmas and New Year! QuantCo is hosting us this time round, featuring talks on architecting data pipelines and search engines for petabyte-scale workloads.
As always, there will be plenty of time for networking, discussions, and snacks 🍕.

Event Details
📍Venue: QuantCo, Prannerstraße 4, 80333 München
📅Date & Time: Tuesday, January 13th, doors open at 18:30

Powering Observability at Petabyte Scale on Snowflake - Georgios Giannikis, Observe, Inc.

Every day, Observe ingests over 1 PB of data and processes more than 20 PB in transformations and queries, all running on Snowflake. Operating at this scale means our pipelines must handle unpredictable traffic spikes without breaking a sweat. In this talk, we'll pull back the curtain on the architecture that got us here. We'll explore how our ingestion pipeline handles custom data types, how we build and maintain materialized views through continuous transformations, and how we schedule work across Snowflake warehouses to balance load and cost. We'll also show how custom indices can turn slow queries into fast ones. If you're curious how Snowflake's analytical engine can power a product at petabyte scale, this one's for you.

About Speaker: Georgios Giannikis is a principal engineer at Observe, Inc. Previously he was working at Oracle on analytical query processing. Georgios obtained his PhD. at ETH Zürich in database systems.

TopK: Designing Low-Latency Search at Billion-Document Scale - Marek Galovic, TopK

TopK is a search engine built from the ground up for unstructured retrieval. It combines dense/sparse vector search, lexical search, powerful filtering, and customizable scoring capabilities in a single, cloud-native system that scales to billions of documents with high ingest throughput and O(10ms) p99 query latencies. In this talk, I'll focus on how TopK is designed on a high-level, including our disaggregated read-write path and distributed compaction, and then dive deep into our columnar file format (.bob) and query engine (reactor), which we built from the ground up to support search at scale.

About Speaker: Marek Galovic is the CEO and a co-founder of TopK. Previously, he worked at Pinecone and Shopify.

Agenda
🔹 18:30: Doors Open
🔹 18:40: Welcome by our hosts (QuantCo)
🔹 18:45: Talk #1: Georgios Giannikis (Observe, Inc.)
🔹 19:30: Pizza & Networking 🍕
🔹 20:00: Talk #2: Marek Galovic (TopK)

Whether you're working on database internals, distributed systems, or
high-performance computing, expect an evening of practical
implementation details and battle-tested approaches.