Research Engineer – Data Systems & Retrieval Innovation

We’re looking for Research Engineers who thrive at the frontier of data systems, vector search, and ML infrastructure. You’ll prototype new algorithms, validate performance, and bring innovations in retrieval and indexing into production.

What You’ll Be Doing

• Design and optimize high-performance vector stores (FAISS, ScaNN, Milvus, or custom).
• Explore graph-based retrieval (KNN graphs, HNSW, hybrid).
• Build LLM-tailored data pipelines: chunking, embedding, metadata enrichment.
• Architect retrieval-augmented generation (RAG) backends.
• Develop semantic search and similarity-based tagging algorithms.
• Prototype, benchmark, and iterate on research ideas rapidly.
• Scale prototypes into distributed, production-grade systems.

What We Need to See

• 5+ years in research engineering or ML infrastructure.
• Strong background in vector search, ANN algorithms, or information retrieval.
• Proficiency in Python and C++ (Rust a plus).
• Hands-on experience with FAISS, ScaNN, or HNSW.
• Familiarity with LLM pipelines and embedding models.

Ways to Stand Out

• Published research or open-source contributions in vector search.
• Experience scaling custom retrieval algorithms in production.
• Background in graph theory or experimental algorithm design.

Why Join Us?
‍

This is a playground for engineers who love to experiment and push boundaries. If you’re excited about inventing the retrieval systems that power the next wave of AI applications, this is the place to do it.