Applied AI Researcher for Trustworthy Autonomous Agents

Improbable; Colombia; A distancia; COP 97.675.000 - 195.351.000; Jornada completa

Descripción de la vacante

Bolter is seeking an AI Researcher to design and run experiments that improve agent reliability and context management. You will prototype evaluations, translate findings into product decisions, and work with lean teams to ship results.

You'll explore state-of-the-art LLMs, tool use, and multi-step workflows, turning research into practical features while maintaining rigorous experimentation and clear communication with the engineering team.

Formación

• Applied AI/ML research experience with LLMs, agentic systems, or production AI reliability.
• Strong experimental design and data analysis capabilities.
• Solid engineering fundamentals to prototype experiments.
• Deep familiarity with LLMs, tool use, context management, and failure modes of agentic systems.
• Strong written communication.
• Ability to work with ambiguity and ship results.
• Experience leveraging AI agents as a force multiplier.
• Passion for craft and product-minded research.

Responsabilidades

• Design and run experiments to test how Bolter's agents behave — reliability, context retention, multi-step task completion, and where they fail.
• Build and own the evaluation layer. Design evals that measure whether agents actually do the work, not just whether they sound plausible.
• Research the frontier. Keep Bolter current on the state of the art in LLM agents, tool use, and reliability - and translate that into what we should build.
• Turn findings into decisions. You produce clear, actionable recommendations the engineering team can ship, not just papers.
• Prototype research into product. Take promising ideas from experiment to working prototype, and hand off what proves useful.
• Shape the research roadmap as Bolter grows.

Conocimientos

Applied AI/ML research

LLM applications

Experiment design

Engineering fundamentals

Written communication

Ambiguity tolerance

Agentic systems

Tool use

Descripción del empleo

Bolter is seeking an AI Researcher to design and run experiments that improve agent reliability and context management. You will prototype evaluations, translate findings into product decisions, and work with lean teams to ship results.

You'll explore state-of-the-art LLMs, tool use, and multi-step workflows, turning research into practical features while maintaining rigorous experimentation and clear communication with the engineering team.