Founding Applied AI Engineer
San Francisco, CAML EngineeringHybrid3+ YOE
Summary
Builds AI-powered concierge systems for luxury travel including recommendation flows, RAG for searches, preference engines, and integrations. Requires 3+ years cloud/AI experience with LLMs, vector search, and production systems; hybrid in SF office.
About the role
What You'll Build
- AI recommendation and booking flows (hotels, dining, flights)
- Retrieval-augmented generation (RAG) systems for dynamic hotel and travel searches
- Preference engines that learn and evolve from member interactions
- Lightweight AI orchestration layers integrated with Zendesk, Slack, and our internal tools
What We’re Looking For
- 5+ years experience developing software in modern environments (Python, Node.js, Go, or similar)
- 3+ years experience deploying and scaling cloud-based applications (AWS, GCP, or similar)
- Deep experience integrating LLMs (OpenAI, Anthropic, Hugging Face) and building production AI systems
- Knowledge of retrieval-augmented generation (RAG), embeddings, and vector search (Pinecone, FAISS, or similar)
- Solid understanding of database design (Postgres, Redis, vector DBs)
- Strong optimization skills, especially for low-latency, high-availability systems
- Product instincts — you think about the end experience, not just the technical specs
- Collaboration skills and a desire to work tightly with product, design, and operations
Skills
PythonNode.jsGoAWSGCPLLMsOpenAIAnthropicHugging FaceRAGPineconeFAISSPostgresRedisvector databases