Adaption
Agent Systems Engineer
San Francisco · Hybrid · Full-time · Posted Sep 24, 2026
- Experience
- 5+ years building production ML or backend systems.
About the job
Build and improve production agent systems that turn customer goals into reliable, multi-step execution using real tools and services.
What you'll do
- Design agent architectures for planning, reasoning, tool use, memory, and external-system integration.
- Improve reliability on long-running tasks through failure recovery and build systems for agents to improve with real use.
- Develop robust agent evaluations, tracing, and observability, while balancing quality, latency, cost, and complexity.
What they ask for
- 5+ years building production ML or backend systems, including taking LLM or agent applications from prototype to production.
- Strong understanding of agent design, including planning, reasoning, tool use, orchestration, and memory.
- Experience building rigorous evaluation systems and agent execution tracing and observability, focused on reproducibility.
- Familiarity with the OpenAI Responses API, MCP, and server- versus client-side execution.
Tools
OpenAI Responses API, MCP
AI focus
Build agents that plan, use tools, recover from errors, and improve with real use; develop evaluations and observability for agent performance.
Model-written summary · the original posting is authoritative