About the role
Responsibilities:
- Build and scale the context and retrieval infrastructure powering AI agents.
- Design ingestion, chunking, embedding, vectorization, and retrieval pipelines.
- Develop integrations with platforms such as Slack, Notion, Mixpanel, Amplitude, and marketing tools.
- Build low-latency semantic search and context APIs.
- Design evaluation frameworks to improve retrieval quality and AI performance.
- Own the architecture of AI knowledge and context systems end-to-end.
Requirements:
- Strong experience in Node.js and TypeScript.
- Hands-on experience building production RAG (Retrieval-Augmented Generation) systems.
- Experience with Vector Databases such as Pinecone, pgvector, Weaviate, or Milvus.
- Strong understanding of Embeddings, Semantic Search, Hybrid Search, and Retrieval Pipelines.
- Experience building third-party integrations using APIs, OAuth, and Webhooks.
- Strong System Design and Distributed Systems knowledge.
- Experience working on AI Agents, LLM-powered applications, or AI Infrastructure platforms.
- Familiarity with AI development tools such as Claude, Cursor, OpenAI, LangChain, or LangGraph.