Agent Systems Engineer - Build Adaptive, Reliable AI Agents

adaption; Argentina; Híbrido; ARS 178.643.000 - 282.852.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Bay Area collaboration

Adaption Passport travel stipend

Lunch stipend

Medical benefits

Paid time off

Descripción de la vacante

adaption is developing core agent systems that translate customer goals into reliable, multi-step executions across real tools and services. You’ll own planning, tool use, memory, and integration with external data, while tackling incomplete information, external failures, and unpredictable traffic.

We seek 5+ years of production ML or backend experience with strong agent design and rigorous evaluation capabilities, including observability and reproducibility.

Formación

• 5+ years building production ML or backend systems.
• 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.

Responsabilidades

• 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 the loops that let agents 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.

Conocimientos

Agent design

Planning & reasoning

Tool orchestration

Memory & data

Observability & reproducibility

Herramientas

OpenAI Responses API

MCP

Server-side execution

Descripción del empleo

adaption is developing core agent systems that translate customer goals into reliable, multi-step executions across real tools and services. You’ll own planning, tool use, memory, and integration with external data, while tackling incomplete information, external failures, and unpredictable traffic.

We seek 5+ years of production ML or backend experience with strong agent design and rigorous evaluation capabilities, including observability and reproducibility.