RAG Systems Engineer
full-time
mid
Posted 6 months ago
Before you apply
Build my evidence-backed draft — freePaste your relevant resume section or 2–4 true bullets. No generic form is sent; any later submission requires your approval of the exact draft and role.
About this role
Build and optimize retrieval-augmented generation pipelines for Perplexity's answer engine. Vector databases, embedding models, and real-time retrieval.
Make AI answers accurate by connecting them to real-time information.
Requirements
Experience building RAG systems in production. Understanding of embedding models and vector databases. Python required. Experience with search infrastructure a plus.
Similar Jobs
Related searches:
On-site Jobs
Mid-Level Jobs
On-site Mid-Level Jobs
Mid-Level NLP & Language AIMid-Level Backend & SystemsMid-Level Data EngineeringMid-Level Data ScienceMid-Level Machine LearningMid-Level AI Agents & RAG
AI Jobs in San Francisco
NLP & Language AI in San FranciscoBackend & Systems in San FranciscoData Engineering in San FranciscoData Science in San FranciscoMachine Learning in San FranciscoAI Agents & RAG in San Francisco
ragpythonvector-databaseembeddingsllmsearchinformation-retrieval
Weekly AI jobs newsletter
Request a confirmation link. Weekly delivery remains paused. Unsubscribe anytime.