Titulo Estágio
Multi-Agent Architecture for AI Agents
Local do Estágio
Coimbra
Enquadramento
This internship will focus on designing and prototyping a multi-agent system where specialized AI agents work together on complex tasks through structured coordination. By moving beyond monolithic chatbot design, the aim is to create a scalable and modular ecosystem where agents—such as Planners, Retrievers, Generators, Validators, and Toolcallers—communicate, delegate responsibilities, and maintain shared memory.
Objetivo
- Design a multi-agent architecture with specialized agents (Planner, Retriever, Generator, etc.)
- Implement communication protocols using LangGraph, CrewAI, AutoGen, or custom orchestrators
- Prototype Google’s Agent-to-Agent (A2A) protocol for intent exchange and multi-agent collaboration
- Develop real-world use cases demonstrating multi-agent workflows
- Evaluate modularity, orchestration strategies, and performance of multi-agent vs single-agent systems
- Establish foundations for multi-agent support in the Intermedia AI Platform
Plano de Trabalhos - Semestre 1
- Onboard to the Intermedia AI Platform and development environment
- Research and compare multi-agent frameworks (LangGraph, AutoGen, CrewAI)
- Design a modular agent architecture with role-specific responsibilities
- Prototype inter-agent communication with shared memory and logging
- Implement a simple use case such as a retrieve–summarize–validate flow
Plano de Trabalhos - Semestre 2
- Implement Google’s Agent-to-Agent protocol and test agent interoperability
- Extend the architecture to support additional tools (e.g., KB search, calendar APIs)
- Prototype a customer support automation use case with task delegation
- Evaluate orchestration, fault tolerance, and scalability across agent flows
Condições
- Monthly stipend of €900, based on a full-time commitment (40 hours per week)
- Hybrid work model: interns are expected to work from the company office 2–3 days per week
- PC or Mac for the duration of the internship
- Integration into a Product Area team, working closely with engineers and stakeholders
- A mentor will be assigned to support the intern’s development and success
Observações
What We Are Looking For:
- Self-motivated individuals with a strong desire to learn and a collaborative mindset
- Final-year Master’s students in Computer Science, Artificial Intelligence, Engineering or related fields
- Demonstrated experience with at least one relevant programming language or technology (e.g., Python, Java or .NET)
- Familiarity with async programming, message queues and pub/sub systems
- Interest in AI agent design and coordination strategies
Orientador
Luis Borges
lborges@intermedia.com 📩