Master Thesis / Internship: Agent Mesh New
- Job Identification: 2297
- Posting Date: 21.02.2025
- Job Schedule: Full time
- Company: ELCA Informatique SA
About Us
We are ELCA, one of the largest Swiss IT tribe with over 2,200 experts. We are multicultural with offices in Switzerland, Spain, France, Vietnam and Mauritius. Since 1968, our team of engineers, business analysts, software architects, designers and consultants provide tailor-made and standardized solutions to support the digital transformation of major public administrations and private companies in Switzerland. Our activity spans across multiples fields of leading-edge technologies such as AI, Machine & Deep learning, BI/BD, RPA, Blockchain, IoT and CyberSecurity.
Job Description
Description
Hot topics in the technical world include Cloud, GenAi, Microservices, Agents, Multi-agents, Data Mesh and Platform Engineering. What about merging all these topics into a single and ambitious internship?
Imagine a network of specialized AI agents, each deeply knowledgeable about its own domain, working together seamlessly to answer queries and solve problems. Like expert colleagues collaborating in a virtual space, these agents can discover each other, share context and work together. This project aims to bring this vision to life, creating a foundation for truly decentralized artificial intelligence that grows and adapt with its organization’s knowledge base.
In this internship, you will focus on designing the protocol for agents to work in a decentralized manner. Then you will implement a proof of concept focusing on microservices, where each repo should be semantically indexed and mastered by a given agent. This agent should be exposed through a Rest API to be queried by humans or other agents. You will also design a service discovery system. Finally, you will design an automated maintenance system ensuring agents stay up to date.
In this internship, you will focus on designing the protocol for agents to work in a decentralized manner.
Your main goal will be to implement a proof of concept focusing on microservices, where each repo should be semantically indexed and mastered by a given agent. This agent should be exposed through a Rest API to be queried by humans or other agents, and easily discoverable through a discovery system service. You will also have to ensure that the agents stay up to date through an automated maintenance system, so that the decentralized system can continue to evolve.
Objectives
- Develop a proof-of-concept implementation of a multi-agent system with at least two specialized agents demonstrating cross-agent querying and knowledge sharing
- Design and implement a standardized communication protocol for inter-agent interactions, including service discovery, capability advertising and query routing
- Establish an automated system for maintaining and updating agent knowledge bases, with monitoring and self-diagnostic capabilities
Our offer
- A dynamic work and collaborative environment with a highly motivated multi-cultural and international sites team
- The chance to make a difference in peoples’ life by building innovative solutions
- Various internal coding events (Hackathon, Brownbags), see our technical blog
- Monthly After-Works organized per locations
Skills required
- Strong programming skills in Python
- Basic knowledge of network, REST APIs and web services
- Solid understanding of distributed systems concepts
- Basic knowledge of Large Language Models and their applications
- Familiarity with document processing and information retrieval
- Good understanding of software engineering best practices
- Being passionate about GenAI, LLMs and AI Agents and constantly being up to date in these fields.