Uni Internship Jan to May 2026 - Collaborative AI Systems with Agentic Frameworks

Apply now »

Date: 25 Jun 2025

Location: SG

Company: Synapxe

Synapxe is the national HealthTech agency inspiring tomorrow’s health. The nexus of HealthTech, we connect people and systems to power a healthier Singapore. Together with partners, we create intelligent technological solutions to improve the health of millions of people every day, everywhere.
 
Are you someone who enjoys problem solving, has a creative and curious mind, and strives to create a better and healthier tomorrow? If you say yes to all, do check out our website and find out more about Internship@Synapxe.
 
Join Synapxe as an intern and see how you can contribute in powering a healthier Singapore. We aim to deliver the best experience for all interns, to create exponential growth and paving your future in the tech industry.

 

This internship aims to explore the forefront of Generative AI by investigating agentic frameworks and the emerging standards for model and agent communication, i.e., MCP and A2A for cross-agentic communication. The intern will research how these technologies enable the development of multi-specialised agents can collaborate to perform complex tasks, i.e., distributed search, information synthesis and multi-step reasoning. This internship will start with building the foundations of understanding various agentic frameworks and design patterns, and then further to prototype and develop a collaborative workflow.

 

The selected intern will participate but not limited to the following:

 

Phase 1: Foundations of Agentic AI and Communication Protocols

 

Agentic Frameworks Research & Comparison:

  • Survey the landscape of agentic AI, including different architectural patterns 9i.e. single agent with tools, multi-agent, etc.)
  • Compare various agentic mechanisms (i.e. group-chat, workflows, grpah-based interactions, planning)
  • Identify core components of intelligent agents (i.e. planning modules, memory management, tool utilisation)

 

Model Context Protocol (MCP) Deep Dive:

  • Explore MCP sepcification, its architecute (host, client, server), and its intended role in standardisation how LLM applications connect with external data sources and tools.
  • Explore MCP's potential for creating more modular and interoperable Gen AI applications by providing a ""universal connector"" for context.

 

Agent-to-Agent (A2A) Deep Dive:

  • Investigate Google's Agent-to-Agent (A2A) focusing on its mechanisms for agent discovery (Agent Cards), task delegation, and information exchange.
  • Explore other A2A equivalents i.e. FastA2A

 

Phase 2: Prototyping a Collaborative Multi-Agent System

 

Agent Design and Role Specialisation:

  • Design a small team of distinct AI agents (i.e. Query Understanding & Planning Agent, Data Retrieval Agent, etc. using MCP/A2A.

 

MCP and A2A integration strategy:

  • Design the MCP/A2A communication flows: how tasks will be decomposed and delegated, how information and intermediate results will be shared between agents, and how overall coordination will be managed.

 

Development:

  • Develop a working prototype that demonstrates:
  • Individual agents performing their specialised functions
  • Agents using MCP (with the available SDKs) to access the required resources
  • Agents communicating and collaborating via A2A principles (emulated or using early A2A libraries/frameworks if available or stable)

 

About you:

  • Be pursuing a Bachelor Degree in Business Analytics, Data Science, Computer Engineering, Computer Science or related discipline
  • Graduating in May/Dec 2026 or May 2027
  • GenAI Fundamentals:
    • Experience with relevant tools and framework like OpenAI API, LangChain/Llama-Index or open source language models
    • Preferred: Some exposure with concepts and applications of Generative AI, i.e. Retrieval Augmented Generation
  • Development Tools Proficiency:
    • Adept in using tools like VS Code for script development and Jupyter notebooks for exploratory analysis
    • Preferred: Knowledge of version control with Git is valuable. The intern will attain the knowledge of building pipelines for RAG, understand the key components for an effective search retrieval, and familiarised with the various implementations for agentic workflows
  • Adept in Python syntax, data structures, algorithms including familiarity with common python libraries, and ability to write clean, efficient, well-documented code
    • Preferred: Back-end development with some exposure to Flask/Fast API
  • Good team player with strong analytical and communication skills
  • Ability to multitask and work effectively as part of a multidisciplinary team
  • Passionate and keen to make a difference to re-imagine the future of HealthTech

 

#LI-YG1

#LI-LK1