Data Conference Databasea Query.Farm index
Speakers

Filip Makraduli

Employers on the program

  1. 2026Superlinked and Imperial College London1 talk
  2. 2025–2026Superlinked6 talks

The year around now

Talks in the past 12 months and announced talks ahead, one row per conference, January to December. Hover a mark for the talk.

Held in the past 12 months Next 12 months Today, Nov 10, 2026

Appearances by year

201920202021202220232024202520262027
  • AI Engineer (World's Fair, Summit and regional editions)
  • Berlin Buzzwords
  • EuroPython
  • Haystack

Talks

DateEventConferenceRoleTitleLinks
Jul 13, 2026EuroPython 2026EuroPythontalkSelf-Hosted Small Models: From OpenAI Lock-In to Open Models
as Superlinked and Imperial College London
OpenAI's embedding API is the default for most Python RAG applications, but it creates real problems at scale: data privacy (every document leaves your…Show less

OpenAI's embedding API is the default for most Python RAG applications, but it creates real problems at scale: data privacy (every document leaves your network), cost (per-token pricing compounds fast), no customization (cannot fine-tune or swap models), and no quality validation.

Video
Jun 29, 2026AI Engineer World's Fair 2026AI Engineer (World's Fair, Summit and regional editions)expo sessionTurning My Obsidian Vault Into a Local AI Engineer
as Superlinked
Video
Jun 29, 2026AI Engineer World's Fair 2026AI Engineer (World's Fair, Summit and regional editions)speakerWeight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards
as Superlinked
Video
Jun 7, 2026Berlin Buzzwords 2026Berlin BuzzwordstalkOne GPU, Four Retrieval Modes: Multi-Model Search Serving
as Superlinked

Competitive search now needs dense embeddings, sparse vectors, ColBERT, and cross-encoder reranking.

Video
Apr 8, 2026AI Engineer Europe 2026AI Engineer (World's Fair, Summit and regional editions)speakerThe Embedding Infrastructure Nobody Built (So We Did)
as Superlinked
Sep 23, 2025Haystack EU 2025HaystackspeakerFrom BM25 to Mixture-of-Encoders: Evaluations for Next-Gen Search and Retrieval Systems
as Superlinked
Modern user queries require a mix of structured and unstructured data in order to achieve satisfactory retrieval performance. This is where traditional search…Show less

Modern user queries require a mix of structured and unstructured data in order to achieve satisfactory retrieval performance. This is where traditional search methods fall short.

Video
Jun 15, 2025Berlin Buzzwords 2025Berlin BuzzwordstalkMixture of Encoders: A Vector-Native Approach to Search
as Superlinked

Mixture of Encoders is a vector-native alternative that models both structured and unstructured data in a unified embedding space.

SlidesVideo

Frequent co-speakers

SpeakerShared eventsShared talksLast together
Alessandro Benedetti2—2026
Alessio Vertemati2—2026
Alex Cheema2—2026
Ankit Jain2—2026
Anna Ruggero2—2026
Atita Arora2—2026
Ben Hylak2—2026
Bilge Yücel2—2026
Brandon Waselnuk2—2026
Celeste Horgan2—2026
Charlie Hull2—2026
Cormac Brick2—2026
Danica Fine2—2026
David Louis Hollembaek2—2026
Evgeniya Sukhodolskaya2—2026

Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.