Deep Search & Retrieval Specialist (LLM)

Our AI agents need to know everything, fast. As our Deep Search Specialist, you’ll work on neural retrieval pipelines, knowledge graph design, and LLM augmentation for in-game and backend systems.

What You’ll Do

  • Build deep search systems for real-time retrieval and context injection
  • Fine-tune embedding models and vector search pipelines
  • Create and maintain custom knowledge graphs across player and agent data
  • Work closely with content and AI teams to ensure semantic fidelity

What You Bring

  • Experience with RAG (Retrieval-Augmented Generation)
  • Background in search ranking, graph databases, and LLM contexts
  • Proficient with FAISS, Pinecone, or similar vector stores
  • Strong understanding of tokenization, prompt injection defense
Job Type: Full Time
Job Location: Remote

Apply for this position

Allowed Type(s): .pdf, .doc, .docx