Retrieval Systems & Vector Search Reviewer
Job Description
Work at IXO
Apply your experience in retrieval-augmented generation engineering to paid work at IXO. You will develop realistic evaluation examples and review AI responses for technical correctness, clear reasoning and practical usefulness. The work calls for explanations that identify the actual defect or trade-off and show how a better answer would address it.
Responsibilities
• Evaluate ingestion, document parsing, chunking, embeddings and metadata choices against retrieval goals.
• Review vector-store implementations with pgvector, Pinecone, Weaviate, Qdrant, Milvus or Vespa, including hybrid search and re-ranking.
• Assess query rewriting, Ragas or TruLens evaluations and retrieval metrics; explain drift, stale-index and adversarial-document failure modes.
• Record the assumptions, supporting evidence and corrections needed for another specialist to follow your review.
Experience and expertise
• 3• years building production RAG or semantic search systems.
• Practical depth in at least two vector databases.
• A thorough understanding of embedding models, distance metrics, and vector index trade-offs (HNSW, IVF, ScaNN).
• Experience with hybrid retrieval and modern re-rankers (cross-encoders, ColBERT).
• Ability to work confidently with Python and at least one orchestration framework (LlamaIndex, LangChain).
• Familiarity with on-premises and cloud deployment of vector stores is an advantage.
Working arrangements and pay
Remote work in these eligible locations: USA, UK, Canada, Germany, Australia. Planning availability: Flexible, 10-25 hours/week. IXO will confirm the actual start and schedule before acceptance. Compensation is $95 • $155/hr USD. The agreed rate, delivery requirements and review criteria are confirmed before work begins.