Production AI Agent Engineer — Reliable Agents & Tooling

Hire Feed; United Arab Emirates; On-site; AED 180,000 - 360,000; Full time

Job summary

Hire Feed is seeking an Agent Engineer to build and operate LLM agents in production. You will ensure visibility into how agents are used within the company and take accountability for their reliability.

You will ship agent systems that real users depend on, design evaluation methods, develop long-running workflows, and monitor costs and resource usage. This role offers the chance to shape internal AI tooling and infrastructure across the organization.

Qualifications

• Experience designing agent systems with real-world reliability requirements.
• Familiarity with agent evaluation frameworks and performance tracking.
• Knowledge of long-running agent execution, including scheduled and persistent tasks.
• Understanding of internal tool adoption dynamics and user behavior patterns.
• Ability to debug and troubleshoot complex distributed agent architectures.
• Proficiency with agent tooling surfaces and interoperability standards.
• Experience integrating agents with company data and internal systems.
• Background in monitoring agent costs and resource utilization.

Responsibilities

• Ship agent systems that real users depend on and resolve issues when they fail.
• Design and implement evaluation methods to measure agent performance improvements or degradations.
• Develop and maintain long-running agent workflows, including scheduled jobs and cloud sandboxes.
• Observe internal user adoption of agent tools and identify barriers to widespread use.
• Build and maintain internal infrastructure for agent memory, reusable skills, and tooling surfaces.

Skills

Agent system design

Evaluation frameworks

Long-running agents

Adoption dynamics

Distributed debugging

Agent tooling

Data integration

Cost monitoring

Job description

Hire Feed is seeking an Agent Engineer to build and operate LLM agents in production. You will ensure visibility into how agents are used within the company and take accountability for their reliability.

You will ship agent systems that real users depend on, design evaluation methods, develop long-running workflows, and monitor costs and resource usage. This role offers the chance to shape internal AI tooling and infrastructure across the organization.