Staff Software Engineer, AI Operations

Oura Oura · Consumer · San Francisco, CA +1 · Software Engineering

Staff Software Engineer on a new, high-velocity, LLM-forward team focused on moving from data and insights to action and orchestration. The role involves architecting backend systems and web interfaces that bridge health data and user utility, building connective tissue for AI models to interact with external APIs and personalized data layers. Responsibilities include rapid prototyping, AI orchestration for LLM-based agents with tool-calling, full-stack ownership, AI-augmented engineering, and applied MLOps for RAG systems.

What you'd actually do

  1. Rapid Prototyping: Move from concept to production in days, not months. You’ll build and validate new interaction layers that bring health intelligence to users where they already are.
  2. AI Orchestration: Design and implement backend logic for LLM-based agents, focusing on reliability, context-window management, and tool-calling (agentic workflows).
  3. Full-Stack Ownership: While backend-heavy, you are comfortable spinning up modern web frontends or jumping into native iOS or Android development to test user experiences and gather immediate feedback. You use the tools available to deploy solutions across platforms and aren’t limited to a single stack.
  4. AI-Native Development: You will be expected to lead the way in AI-augmented engineering—utilizing tools like Claude Code, Cursor, and automated refactoring to maintain a velocity that traditional teams can't match.
  5. Systems Integration: Build secure, scalable integrations between our internal intelligence engine and third-party service providers.
  6. Applied MLOps: You understand that "AI in production" is more than just an API call. You have experience with MLOps best practices, including model monitoring, evaluation frameworks (LLM-as-a-judge), versioning, and deploying scalable data pipelines that fuel RAG systems.

Skills

Required

  • 5+ years building and maintaining production systems
  • Backend language expertise (Python, or Node.js)
  • Strong grasp of modern frontend frameworks (React/Next.js) or native development (Swift/Kotlin)
  • Experience building with OpenAI, Anthropic, or LangChain/LlamaIndex
  • Understanding of prompt engineering and RAG
  • Experience with MLOps best practices
  • Experience with model monitoring, evaluation frameworks (LLM-as-a-judge), versioning, and deploying scalable data pipelines
  • Security & Privacy Conscious system design
  • Experience with AI-augmented engineering tools

Nice to have

  • Digital Health or MedTech space experience
  • Building conversational interfaces or automated concierge services
  • Contributions to open-source AI projects
  • Portfolio of weekend projects leveraging LLM capabilities

What the JD emphasized

  • AI-augmented engineering
  • LLM-based agents
  • tool-calling
  • RAG systems
  • LLM Power User
  • prompt engineering
  • RAG (Retrieval-Augmented Generation)

Other signals

  • LLM-based agents
  • AI-native development
  • Rapid prototyping
  • Systems integration