AI Researcher - Bolter

📋 Description

• Design and run experiments to test how Bolter's agents behave - reliability, context retention
• Build and own the evaluation layer - design evals that measure whether agents actually do the work.
• Research the frontier - keep Bolter current on the state of the art in LLM agents, tool use, and
• Turn findings into decisions - produce clear, actionable recommendations the engineering team can
• Prototype research into product - take promising ideas from experiment to working prototype.
• Shape the research roadmap as Bolter grows.

🎯 Requirements

• A track record of applied AI/ML research - ideally in LLM application design, agentic systems
• Strong experimental design and analysis skills.
• Strong engineering fundamentals - ability to prototype experiments.
• Deep familiarity with LLMs, tool use, context management, and failure modes of agentic systems.
• Strong written communication.
• Rigorous but pragmatic approach - knowing when findings are strong enough to act on.

🎁 Benefits

• Experience with LLM evals, hallucination mitigation, or production AI reliability at scale.
• Experience building or evaluating agentic systems, tool use, or autonomous workflows.
• A public track record - papers, open source, blog posts, side projects.
• Experience in product-led research - where output is a shipped feature.