Senior RAG Engineer

1 month ago

Copenhagen, Denmark +5 moreSenior

Responsibilities

Own the retrieval pipeline from document parsing and chunking through embeddings, indexing, ingestion, and reindexing.
Design hybrid semantic and keyword search in Qdrant, including ranked-list fusion, metadata filtering, and reranking.
Build agentic retrieval capabilities such as query decomposition, document-navigation tools, multi-step loops, and cost and latency controls.
Create golden sets, retrieval metrics, regression tests, and tracing to evaluate retrieval quality and diagnose incorrect answers.
Ship reliable Python and FastAPI services with ingestion, embedding, and reindexing running as background jobs.
Maintain strict data security and tenant isolation for confidential client documents.
Improve retrieval quality across multiple client languages, including cases involving compounding and inflection.
Own production maintenance, technical debt, and systems end to end.

At least five years of experience building production backend systems.
At least two years shipping production retrieval or RAG systems used by real users.
Experience diagnosing production retrieval regressions and building and maintaining golden evaluation sets.
Production experience operating vector indexes, including selecting index parameters, managing memory and latency trade-offs, and reindexing without downtime.
Strong Python skills and experience with FastAPI or a close equivalent, PostgreSQL, and Redis under load.
At least five years of Python experience, at least two years of FastAPI experience, and at least two years of production vector-database experience.
Experience with embedding models, retrieval-quality metrics, OCR-heavy document ingestion at scale, information retrieval, BM25, NDCG, recall@k, and search abstractions spanning multiple backends.
Experience with AI coding assistants and the ability to review AI-written code effectively.
Ability to work independently in a fast-changing startup environment.

Fully remote across the EEA, including Norway, with employment through a company entity or local employer of record depending on location.
Requires existing authorization to work in the country of residence; the company does not sponsor visas for this role.
Opportunity to shape product and culture at a growing AI venture.
Collaborative, high-energy team with talented peers.
Flexible, English-speaking work environment.

11-50 employees