Agents Research Lead

About the Company

General Intelligence Company is building highly-capable autonomous agents for startups with the goal of enabling the one-person, one-billion-dollar company. We are a small, elite team working on the most interesting problems in agents.

Responsibilities

• Design and run experiments across model selection, prompting, tool-use, memory, planning, and multi-agent coordination
• Lead evaluations by building datasets, success criteria, and continuous benchmarks for real workflows
• Push performance by reducing tail latency, failure modes, and improving determinism, throughput, and cost
• Partner with engineering and product teams to ship weekly
• Mentor a small, senior team and set standards for experiment design, code quality, and documentation
• Pursue advanced memory research for multi-agent systems

Requirements

• 5–8+ years in applied ML/AI, ML systems, or research engineering
• Deep experience with LLMs and agentic systems including prompting, function calling, planning, and retrieval
• Track record of moving research from paper to prototype to production using Python
• Published papers in AI/ML directly applicable to modern agentic systems
• Experience building reliable evaluation harnesses and curated datasets for multi-step tasks
• Proven ability to ship improvements that move core business metrics
• High-ownership startup experience preferred

Preferred Qualifications

• Experience with orchestration frameworks
• Knowledge of streaming/real-time state sync
• Experience with safety/guardrails
• Experience with reinforcement or online evaluation loops