Intern (AI Systems)

WHAT YOU MAY WORK ON

• Designing single-agent and multi-agent systems 

• Building tool-use and function-calling workflows 

• Designing feedback loops for agents to evaluate and improve their outputs 

• Agent planning, memory, delegation, and coordination • Building evaluation frameworks for agent performance 

• Designing systems where agents interact with software, data, and other AI models 

• Developing autonomous workflows with human review where appropriate 

• Improving reliability, observability, and failure recovery in agent systems 

• Exploring approaches to long-running and self-improving AI systems

WHAT WE'RE LOOKING FOR

We are looking for someone who understands modern AI systems and agent design, and is comfortable thinking about how multiple components work together.

• Designing agent architectures and workflows 

• Working with multi-agent systems 

• Designing feedback and evaluation loops 

• Thinking about tool selection, planning, and task decomposition 

• Building systems that can operate over multiple steps 

• Evaluating where and why agents fail 

• Reading current AI research and applying relevant ideas 

• Building and testing ideas independently

WHO SHOULD APPLY

We care more about what you have built and how you think about AI systems than your title or degree. Graduate students are ideal, but undergraduates and self-taught candidates with strong AI projects are also encouraged to apply.

To apply: Please include your resume/CV, portfolio or GitHub, and 1-3 projects or research efforts you are particularly proud of.

Nunca envíes tu información personal (DNI, foto,...), datos bancarios ni realices ningún pago para solicitar un empleo