RESEARCHER, AGENTS FOR AUTOMATED DISCOVERY

The role

You will research multi-agent systems that conduct automated machine learning research and discovery. You will design how agents plan, decompose problems, choose next steps, evaluate outputs, and recover from mistakes.

What you will do

• Design methods to improve agent planning, task decomposition, tool use, context management, and failure recovery
• Develop multi-agent coordination patterns for sharing context, dividing labor, and supervising each other
• Build and maintain evaluation frameworks for agent capability on open-ended tasks
• Run rigorous experiments including controls, ablations, and statistical significance
• Co-design agent architectures with engineering teammates and ship methods into production
• Read literature across agentic ML, planning, RL, and tool-use
• Share findings internally
• Help shape research direction across the team

Required qualifications

• Strong track record of ML research with focus on agents, RL, LLMs, planning, tool use, or multi-agent systems
• 5+ years of hands-on research experience in industry or academia
• Comfort designing experiments and running them end-to-end at scale
• Track record of building evaluation frameworks for capabilities that aren't easily benchmarked
• Bias toward shipping research, not handing it off
• Strong written communication
• Comfort with ambiguity
• Published research at NeurIPS, ICML, ICLR, COLM, RLC, or comparable venues

Nice to have

• PhD in ML, statistics, CS, or adjacent
• Published research on agentic systems, tool use, long-horizon planning, multi-agent coordination, or self-improvement methods
• Open-source contributions in the agentic ML ecosystem
• Experience with reasoning models, chain-of-thought / scratchpad methods, or supervised fine-tuning for agentic behaviors
• Background in evaluation methodology for capabilities that don't have established benchmarks

About the company

makermaker.ai is a small, well-funded team building autonomous research agents for recursive self-improvement.