LLM Agent Engineer - Specialist

Obsidian; Mumbai; On-site; INR 1,500,000 - 3,000,000; Full time

Job summary

Obsidian in Mumbai 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 that real users depended on and have been on the hook when it broke, and you have figured out how to tell whether a change improves performance.

We want to hear how you think about agent reliability, evaluation, adoption, and the tradeoffs you have made in real systems. Bring war stories.

Qualifications

• Shipped an agent used by real users
• Experience evaluating agent performance after changes
• Experience operating long-running or scheduled agents

Responsibilities

• Build and operate LLM agents in production with visibility into usage and costs
• Ensure reliability and performance of agents in live environments
• Share concrete war stories about tradeoffs and design decisions in real systems
• Participate in a short conversational AI interview and discuss agent reliability and adoption

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.