AI Engineer Intern – RAG / LLMs / Agentic AI

GenX Leadership Academy | Talent Accelerator Program

About the Opportunity

GenX is looking for a motivated and technically capable AI Engineer Intern to join our four-month Talent Accelerator Program.

This internship is aimed at developers with practical experience building AI-powered applications, particularly using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and agentic AI systems.

The ideal candidate has a strong Python development background, experience building APIs with FastAPI, and an understanding of how to integrate LLMs into practical applications. We welcome candidates with mid-junior through senior-level experience who are interested in contributing to real-world AI projects.

About GenX

GenX is a company registered in Berlin, Germany, focused on developing innovative digital solutions and creating opportunities for professional growth through practical learning and collaboration.
Through the GenX Leadership Academy, we provide structured development opportunities that combine hands-on experience, mentorship, and exposure to real-world projects.

The Role

As an AI Engineer Intern, you will contribute to the design, development, and implementation of AI-powered applications and intelligent systems.

You will work with technologies such as Python, FastAPI, LLMs, RAG architectures, and agentic AI frameworks to build applications that can retrieve information, reason over context, interact with tools, and automate workflows.

Depending on your experience, you may take ownership of individual AI features, develop end-to-end solutions, or contribute to the architecture of more advanced AI systems.

Key Responsibilities

• Develop AI-powered applications using Python and modern LLM technologies.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines.
• Integrate Large Language Models through APIs and model-serving platforms.
• Build backend services and APIs using FastAPI.
• Develop AI agents capable of using tools, executing tasks, and interacting with external systems.
• Work with agentic AI frameworks and orchestration patterns.
• Implement document ingestion, processing, chunking, embedding, retrieval, and context management workflows.
• Work with vector databases and vector search technologies.
• Improve the quality, accuracy, relevance, and reliability of LLM-generated responses.
• Experiment with prompt engineering, structured outputs, and context optimization.
• Implement evaluation methods to assess RAG and LLM performance.
• Integrate AI services with existing applications, databases, and backend systems.
• Apply appropriate security, privacy, and error-handling practices to AI applications.
• Collaborate with developers and other team members to deliver practical AI solutions.
• Document technical implementations and contribute to code reviews.

Required Skills and Qualifications

• Strong practical 3+ years experience with Python.
• Experience developing backend applications and APIs using FastAPI.
• Practical experience working with Large Language Models (LLMs).
• Understanding of Retrieval-Augmented Generation (RAG) architectures and workflows.
• Experience building or integrating AI-powered applications.
• Understanding of embeddings, semantic search, vector databases, and retrieval techniques.
• Experience with prompt engineering and LLM API integration.
• Knowledge of agentic AI concepts, including tool calling, function calling, and multi-step task execution.
• Familiarity with at least one agentic AI framework, such as LangChain, LangGraph, LlamaIndex, or a comparable framework.
• Understanding of REST APIs and backend integration.
• Familiarity with Git and collaborative software development workflows.
• Ability to troubleshoot, test, and optimize AI-powered systems.
• Good communication and collaboration skills.
• English proficiency sufficient for remote team communication.
• Experience Levels
• We welcome applicants at different stages of their AI engineering careers:
• Mid-Junior
• Approximately 1+ year of practical Python or AI application development experience, or equivalent hands-on project experience.
• Familiarity with LLM APIs and basic RAG concepts.
• Able to build simple AI-powered applications and integrate APIs.
• Basic experience with FastAPI or another Python backend framework.
• Motivated to deepen knowledge of RAG pipelines, vector databases, and AI agents.
• Experienced / Mid-Level
• Strong practical experience developing Python-based AI applications.
• Experience implementing RAG pipelines, including document processing, embeddings, retrieval, and response generation.
• Comfortable building backend services with FastAPI.
• Experience integrating LLMs into production-oriented applications.
• Familiarity with agentic workflows, tool calling, and orchestration frameworks.
• Able to independently develop, test, and improve AI application features.
• Senior
• Extensive experience designing and developing LLM-powered applications and AI systems.
• Strong understanding of advanced RAG architectures, retrieval optimization, and LLM evaluation.
• Experience building agentic AI systems and multi-step workflows.
• Strong Python and FastAPI development capabilities.
• Able to contribute to AI system architecture, scalability, reliability, and technical decisions.
• Experience with deployment, monitoring, security, and performance optimization of AI applications.
• Comfortable mentoring or supporting other developers where appropriate.
• Interested in contributing within the scope and part-time structure of an internship.

Who We're Looking For

We are looking for someone who:

• Is genuinely interested in applied AI and the development of intelligent systems.
• Has hands-on experience building with LLMs rather than only theoretical knowledge.
• Understands how to connect LLMs with external data, APIs, tools, and business workflows.
• Enjoys experimenting with RAG architectures and agentic AI approaches.
• Can translate technical requirements into working AI applications.
• Takes ownership of assigned tasks and follows through.
• Can work independently while collaborating effectively with a remote team.
• Communicates clearly and is open to feedback.
• Keeps up with developments in LLMs, AI agents, and the broader AI engineering ecosystem.

What You Can Expect

• Hands-on experience developing real-world AI-powered applications.
• Practical exposure to RAG architectures, LLM integrations, and agentic AI systems.
• Opportunities to work with Python, FastAPI, vector databases, and modern AI frameworks.
• Collaboration with an international and distributed team.
• Opportunities to strengthen technical and problem-solving skills.
• Feedback and opportunities for professional development.
• The opportunity to contribute to practical AI projects through the GenX Leadership Academy.

Important Notes

• This is a four-month internship, not a freelance or independent contractor position.
• The internship is part-time and remote.
• Applicants should be able to commit approximately 16–20 hours per week.
• Candidates with mid-junior, mid-level, or senior experience are welcome.
• Practical experience building AI applications is strongly preferred.
• The internship is intended to provide practical project experience and professional development.
• Specific internship compensation and applicable arrangements will be communicated during the selection process.

Application Screening Questions

Please answer the following questions when applying:

• Do you have practical experience developing applications with Python?
• Have you built backend services or APIs using FastAPI?
• Have you worked directly with Large Language Models (LLMs)?
• Have you implemented a Retrieval-Augmented Generation (RAG) pipeline?
• Have you worked with embeddings and semantic search?
• Have you used a vector database, such as Pinecone, Weaviate, Qdrant, Chroma, or FAISS?
• Have you integrated LLM APIs such as OpenAI, Anthropic, or comparable providers?