Remote, Remote, North America, Europe TG
Scope is looking for a research engineer for a project-based contract of about two months, fully remote, paid by the hour. The project: build a relevance benchmark for channel search in 6+ languages (query sets, relevance judgments, nDCG and recall@k), measure retrieval quality by language and query type, and improve the fusion of semantic and lexical results. How Python is used: the whole project is Python.
The search service is a FastAPI application, embeddings run on ONNX Runtime from Python, and the benchmark, evaluation scripts and experiments are written in Python. Stack: Python, FastAPI, Qdrant, multilingual-e5 on ONNX Runtime, PostgreSQL with pg_trgm, Reciprocal Rank Fusion. Experience in information retrieval, search or NLP engineering Hands-on work with dense retrieval and hybrid search in production Strong Python Experience with a vector database (Qdrant, Milvus, Weaviate or similar) Experience with multilingual embedding models Written English