Back to internships
Agentic AI · Internship

Agentic AI Intern at Evore Labs.

Help build the goal-directed agents and Model Context Protocol that run our research loop.

Stipend
£1,300 / month
Duration
2 months
Work
Remote
Location
Remote-first · UK
The Role

What you will own.

You will help build the agents and the Model Context Protocol that let our research loop run with minimal human instruction. That means designing systems where LLM-driven agents plan, call tools, coordinate with one another, and stay observable and governable throughout. It is equal parts systems engineering and applied AI — you will care about typed interfaces, reliability and evaluation as much as clever prompting.

Responsibilities

  • Prototype goal-directed agents that plan, use tools and coordinate.
  • Contribute to typed context and capability interfaces (the Model Context Protocol).
  • Build evaluation harnesses that measure agent reliability, not just demos.
  • Add tracing and observability so agent behaviour is auditable.
  • Design guardrails and human-in-the-loop checkpoints.

Qualifications

  • Experience building LLM-driven or agentic prototypes.
  • Strong systems and API design instincts; fluent Python and/or TypeScript.
  • Understanding of tool use, function calling and context management.
  • A bias toward reliability, evaluation and reproducibility over demos.
  • Clear technical writing.

Nice to have

  • Work with agent frameworks, MCP or orchestration systems.
  • Distributed systems or message-passing exposure.
  • Prompt or behaviour evaluation experience.
Learning

What this track teaches.

You will learn

  • How to make autonomy reliable and auditable.
  • Protocol design across models, tools and data.
  • Evaluating open-ended agent behaviour.
  • Coordinating many specialised agents into one system.
Tools

The stack around the work.

Python
TypeScript
MCP
LLM APIs
Async / queues
OpenTelemetry

Apply

Send the work that proves the fit.

Tell us what you have built, tested or discovered. A researcher or engineer reads every application.

Apply for this roleView all internships