Software Engineer, Agent Architecture

Sierra Sierra · AI Frontier · San Francisco, CA · Engineering

Software Engineer, Agent Architecture role focused on building core systems for AI agents, including orchestration, runtime, and primitives. The role also involves improving retrieval and grounding for accurate responses and building evaluation systems to measure agent quality. Experience with AI-powered systems, agent frameworks, retrieval, evaluation, and LLM-based applications is preferred.

What you'd actually do

  1. Build the core systems that power agents. You’ll work on the Agent SDK — the orchestration engine, runtime, and primitives that define how agents reason, take actions, and interact with users and systems.
  2. Design the agentic loop. What primitives do we need to build agents that are steerable and verifiable, while still conversational and adaptive? You’ll help define how agents operate in real-world environments.
  3. Improve retrieval and grounding. You’ll build systems that ensure agents provide accurate, trustworthy responses by effectively retrieving and using knowledge.
  4. Build evaluation systems. You’ll design frameworks that allow us and our customers to measure and improve agent quality over time.

Skills

Required

  • Strong software engineering fundamentals
  • experience building production systems
  • 4+ years hands-on experience building production products and systems
  • Degree in Computer Science or related field, or equivalent professional experience

Nice to have

  • Experience building AI-powered systems or agent frameworks
  • Experience with retrieval, evaluation systems, or LLM-based applications
  • Experience building developer platforms or SDKs
  • Experience with Go and Typescript

What the JD emphasized

  • production systems
  • production products and systems
  • AI-powered systems
  • agent frameworks
  • retrieval
  • evaluation systems
  • LLM-based applications

Other signals

  • building agent systems
  • retrieval and grounding
  • evaluation systems