LLM Agent Engineer - Specialist

Obsidian; San Francisco (CA); On-site; USD 170,000 - 250,000; Full time

Job summary

Obsidian in San Francisco is seeking engineers to build and operate LLM agents in production. You will ship an agent that real users depend on, measure whether changes improve or degrade it, and ensure it can run long beyond a single request—from scheduled jobs to cloud sandboxes.

You will understand how agents are adopted inside the company, and focus on the less-talked-about layers: internal monoagents wired to company data, shared memory, reusable skills and playbooks, and how tools and MCP

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.