Back
Strong employer brand, remote role, popular AI title, mid-level experience, and metro location increase applicant competition.
Highly specialized enterprise retrieval, ACL, and RAG expertise limits cross-industry transferability.
Explicit 3+ years and mandatory IR/vector/search tools, embeddings, cloud, and permission-model expertise tighten filters.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Build and own a unified, permission-aware enterprise retrieval layer integrating diverse systems (Google Drive, Salesforce, Zendesk, Jira, etc.) for AI agents.
Design and implement hybrid retrieval pipelines combining lexical, dense vector, and structured search with freshness and permission constraints.
Develop evaluation metrics, production-grade observable systems, and mentor teammates to improve retrieval architecture and engineering quality.
3+ years experience building production search, retrieval, knowledge-base, or recommendation systems (5+ preferred).
Proficiency in backend languages such as Python, Go, or Java.
Hands-on experience with search engines like OpenSearch, Elasticsearch, Solr, or Vespa and strong IR fundamentals.
Experience with vector search/embeddings tools (FAISS, Pinecone, Weaviate, etc.) and familiarity with SaaS API integrations and enterprise ACL models.
Experienced senior engineer with deep expertise in enterprise-scale, multi-source retrieval systems involving complex permission models.
Skillful in hybrid search architectures merging lexical, semantic, and structured data retrieval with strong evaluation rigor.
Comfortable working across multiple cloud platforms, large-scale distributed systems, and collaborating with ML/product/security teams to operationalize AI in enterprise contexts.