LLM Agent Engineer - Production

Mercor; Berlin; On-site; EUR 70,000 - 110,000; Full time

Benefits offered by this job

Interview compensation

Job summary

Obsidian seeks engineers to build and operate LLM agents in production, with real visibility into how agents are used inside a company. You have likely shipped an agent used by real users and will discuss its reliability and impact after changes.

Applying starts with a short conversational AI interview. We want to hear how you think about agent reliability, evaluation, and adoption, and the tradeoffs you have made in real systems. The interview pays $100 to $500 depending on depth of experience.

Qualifications

• Experience shipping an agent used by real users.
• Ability to evaluate impact of changes on agent performance.
• Experience with long-running workflows and scheduled jobs.

Responsibilities

• Build and operate LLM agents in production.
• Provide visibility into how agents are used inside a company.
• Discuss reliability, evaluation, and adoption with teams.

Skills

LLM agents

Production deployment

Agent reliability

Evaluation of changes

Long-running jobs

Job description

We are looking for engineers who build and operate LLM agents in production, and who have real visibility into how agents are actually used inside a company.

You have probably:

• Shipped an agent that real users depended on, and been on the hook when it broke.
• Figured out how to tell whether an agent got better or worse after a change.
• Run agents that outlive a single request: scheduled jobs, long-running work, cloud sandboxes.
• Watched your org build an internal assistant, and seen who adopted it and who quietly did not.

We are especially interested in the layers most people do not talk about: internal monoagents wired into company data, shared company memory, reusable skills and playbooks, the tool and MCP surfaces agents call, and how anyone sees what agents did and what they cost.

Applying starts with a short conversational AI interview. No coding, no take-home. We want to hear how you actually think about agent reliability, evaluation, and adoption, and the tradeoffs you have made in real systems. Bring war stories. The messier and more specific, the better.

If that screen stands out, we will invite you to a live 30 minute conversation with our team. We pay $100 to $500 for that conversation, paid on completion of the call, with the amount depending on depth of experience.