Julius Lipp

AI & Search

Brief

My journey as a Founder started when a surfing accident left me in bed for a few months. I had way too much time to think and realized I really want to build something that matters. When I got to Google, I discovered how fun software engineering can be—especially when you're on a team that's genuinely passionate about what they do. Working on LLMs in their early days (that same team is now building Google Gemini) gave me a glimpse of AI's massive potential and shaped everything that followed.

I co-founded Mixedbread to build the next generation of search. Our open-source models reached over 60 million downloads on Hugging Face—about 5.15% of all HF downloads in 2024! I'm incredibly grateful to the brilliant team who made this possible. Their talent and dedication showed that a small, focused group can compete with the world's top AI labs.

I'm fascinated by the gap between what LLMs can already do and what we're actually building with them. While the models keep advancing, most applications barely scratch the surface of their potential. I'm excited to explore creative new ways to apply them and see how software evolves as we push these boundaries.

Always happy to chat, find me on LinkedIn or X.

Timeline

Nov 2019Jan 2023

Software Engineer @ crossnative

Built modern web applications

May 2014Nov 2019

Dishwasher @ various restaurants

Washed dishes and kept the kitchen clean

Open Source & Contributions

ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking

Jun 4, 2025

Two-stage approach combining GRPO with fine-grained logit aggregation, enabling SMLs to outperform much larger models at document reranking.

The Hidden Ceiling: How OCR Quality Limits RAG Performance

May 14, 2025

Blog post demonstrating how OCR errors create a performance ceiling for RAG systems, and how multimodal models can improve retrieval by a good margin.

Baked-in Brilliance: Reranking Meets RL with mxbai-rerank-v2

Mar 13, 2025

Second-generation reranking models using reinforcement learning, supporting 100+ languages with up to 32k token context.

Every Byte Matters: Introducing mxbai-embed-xsmall-v1

Oct 14, 2024

Compact 22.7M parameter embedding model with support for binary quantization and matryoshka embeddings.

Baking in Performance - Dynamic Batching with Batched

Sep 16, 2024

A library that adds dynamic batching to inference systems, grouping requests/tensors to maximize model throughput.

Getting Better with Baguetter - New Retrieval Testing Framework

Aug 23, 2024

Open-source information retrieval testing framework supporting sparse, dense, and hybrid search with unified benchmarking.

BM𝒳: A Freshly Baked Take on BM25

Aug 12, 2024

Enhanced lexical search algorithm improving BM25 with entropy-weighted similarity and weighted query augmentation.

Open Source Gets DE-licious: Mixedbread x deepset German/English Embeddings

Jul 18, 2024

Collaboration with deepset producing high-performance German/English embedding models with support for binary quantization/MRL.

ColBERTus Maximus - Introducing mxbai-colbert-large-v1

Mar 19, 2024

ColBERT model for reranking and retrieval, outperforming other ColBERT and cross-encoder models on BEIR.

Fresh 2D-Matryoshka Embedding Model

Mar 15, 2024

Embedding model supporting Matryoshka for both hidden layers and embeddings, enabling flexible 2D dimensionality reduction.

Open Source Strikes Bread - New Fluffy Embedding Model

Mar 8, 2024

State-of-the-art embedding model (mxbai-embed-large-v1) trained on 700M+ data pairs, outperforming OpenAI's text-embedding-v3.

Boost Your Search With The Crispy Mixedbread Rerank Models

Feb 29, 2024

Family of open-source reranking models (xsmall, base, large).

The Hidden Ceiling: How OCR Quality Limits RAG Performance

May 14, 2025

Blog post demonstrating how OCR errors create a performance ceiling for RAG systems, and how multimodal models can improve retrieval by a good margin.

Baked-in Brilliance: Reranking Meets RL with mxbai-rerank-v2

Mar 13, 2025

Second-generation reranking models using reinforcement learning, supporting 100+ languages with up to 32k token context.

Every Byte Matters: Introducing mxbai-embed-xsmall-v1

Oct 14, 2024

Compact 22.7M parameter embedding model with support for binary quantization and matryoshka embeddings.

Baking in Performance - Dynamic Batching with Batched

Sep 16, 2024

A library that adds dynamic batching to inference systems, grouping requests/tensors to maximize model throughput.

Getting Better with Baguetter - New Retrieval Testing Framework

Aug 23, 2024

Open-source information retrieval testing framework supporting sparse, dense, and hybrid search with unified benchmarking.

BM𝒳: A Freshly Baked Take on BM25

Aug 12, 2024

Enhanced lexical search algorithm improving BM25 with entropy-weighted similarity and weighted query augmentation.

Open Source Gets DE-licious: Mixedbread x deepset German/English Embeddings

Jul 18, 2024

Collaboration with deepset producing high-performance German/English embedding models with support for binary quantization/MRL.

ColBERTus Maximus - Introducing mxbai-colbert-large-v1

Mar 19, 2024

ColBERT model for reranking and retrieval, outperforming other ColBERT and cross-encoder models on BEIR.

Fresh 2D-Matryoshka Embedding Model

Mar 15, 2024

Embedding model supporting Matryoshka for both hidden layers and embeddings, enabling flexible 2D dimensionality reduction.

Open Source Strikes Bread - New Fluffy Embedding Model

Mar 8, 2024

State-of-the-art embedding model (mxbai-embed-large-v1) trained on 700M+ data pairs, outperforming OpenAI's text-embedding-v3.

Boost Your Search With The Crispy Mixedbread Rerank Models

Feb 29, 2024

Family of open-source reranking models (xsmall, base, large).

ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking

Jun 4, 2025

Two-stage approach combining GRPO with fine-grained logit aggregation, enabling SMLs to outperform much larger models at document reranking.

BM𝒳: A Freshly Baked Take on BM25

Aug 12, 2024

Enhanced lexical search algorithm improving BM25 with entropy-weighted similarity and weighted query augmentation.

Baking in Performance - Dynamic Batching with Batched

Sep 16, 2024

A library that adds dynamic batching to inference systems, grouping requests/tensors to maximize model throughput.

Getting Better with Baguetter - New Retrieval Testing Framework

Aug 23, 2024

Open-source information retrieval testing framework supporting sparse, dense, and hybrid search with unified benchmarking.