5 months ago
Base Salary
$130k - $500k/yr
Responsibilities
- Build and maintain MCP servers that let agents read project state, take management actions, and trigger communications.
- Design and implement evaluation frameworks to measure agent decision quality and improve systems through feedback loops.
- Develop action queues and playbook orchestration systems for multi-step workflows with conditional logic.
- Instrument agent systems end-to-end to capture outcomes and improve evaluation metrics.
- Collaborate with operators to identify automation opportunities and translate workflows into robust agent behaviors.
- Debug and harden agent systems in production for reliability at scale.
- Contribute to foundational infrastructure and patterns used across the company.
Requirements
- Strong backend engineering fundamentals in Python or an equivalent modern language.
- Experience building with LLM APIs, including tool use, structured outputs, and multi-step reasoning workflows.
- Experience designing evaluation frameworks and analyzing agent failure modes.
- Ability to ship quickly and iterate on systems that interact with the real world.
- Understanding of distributed systems, APIs, and production infrastructure.
- Full-stack experience is preferred.
Benefits
- Generous equity grant vesting over four years
- Housing bonus for employees living within 0.5 miles of an office
- Monthly meal stipend
- Free Equinox membership
- Health insurance
- In-person work five days per week in San Francisco, New York City, or London
Tech Stack
Categories
About Mercor
We find the best experts in every professional domain and put their knowledge to work training frontier models. Through APEX, we measure whether those models can actually perform economically valuable work. We're also bringing that expertise to enterprises: deploying custom AI agents, staffing teams with vetted domain experts, and helping organizations encode their own knowledge into AI systems.