Agent Maestro

The role

You will build intelligent orchestration, self-healing workflows, and evaluation systems. You will experiment with new models, agent frameworks, and prompting strategies.

What you will do

• Build intelligent orchestration that assigns the right type of agent to the right task
• Develop self-healing workflows that detect, diagnose, and resolve agent blocks
• Experiment with new models, agent frameworks, prompting strategies, and tool-use patterns
• Build evaluation and benchmarking systems
• Produce high quality, clean, human-reviewable code
• Review code

Required qualifications

• Experienced building multi-agent systems or complex LLM-powered applications in production
• Comfortable with all of Python, TypeScript, Ruby
• Strong systems thinker
• Self-directed and experimental
• 3+ years of professional engineering experience
• At least 1 year deeply focused on AI/LLM applications

Nice to have

• Built or contributed to an agent framework, MCP server, or agent evaluation benchmark
• Shipped a product where AI agents operate autonomously
• Experience with Rails

Benefits

• Highly competitive salary
• Meaningful equity
• Flexible PTO
• Parental leave
• Health insurance
• Employee-friendly equity terms
• Premium equipment
• Practically unlimited token budget

About the company

Superconductor is building the autonomous software organization, a platform where agents find work in customer emails, bug reports, and other sources. The team consists of 7 people and was formerly co-founded by the creators of Gradescope.