Senior Agent Systems Engineer — Real-World AI Orchestration

adaption; San Francisco (CA); On-site; USD 170,000 - 210,000; Full time

Benefits offered by this job

Flexible work: Bay Area in-person +全球分

Adaption Passport: Travel stipend

Lunch Stipend

Well-Being: Medical benefits & PTO

Job summary

adaption is seeking an experienced engineer to build the core agent systems that convert customer goals into reliable, multi-step actions across real tools and services. You will tackle planning, tool use, memory, and error recovery in production environments in a Bay Area setting.

You will work on end-to-end agent reliability, evaluations, and optimizations for long-running tasks, with emphasis on reproducibility and robust observability.

Qualifications

• 5+ years building production ML or backend systems, including taking LLM or agent applications from prototype to production.
• Strong understanding of agent design: planning, reasoning, tool use, orchestration, and memory.
• Experience building rigorous evaluation systems, plus execution tracing and observability for agents, with a focus on reproducibility.
• Familiarity with the OpenAI Responses API, MCP, and server- versus client-side execution.

Responsibilities

• Design agent architectures for planning, reasoning, tool use, memory, and integration with external systems and data.
• Improve reliability on long-running, multi-step tasks, including failure recovery.
• Build loops that allow agents to improve with real use, so performance compounds over time.
• Develop evaluations that measure agent performance and resist being gamed.
• Make practical tradeoffs between quality, latency, cost, and complexity.

Skills

Agent design

Evaluation systems

LLM/Agent production

Adaptability

Tools

OpenAI Responses API

MCP

Server-side execution

Job description

adaption is seeking an experienced engineer to build the core agent systems that convert customer goals into reliable, multi-step actions across real tools and services. You will tackle planning, tool use, memory, and error recovery in production environments in a Bay Area setting.

You will work on end-to-end agent reliability, evaluations, and optimizations for long-running tasks, with emphasis on reproducibility and robust observability.