Junior AI Application Engineer – AI Products (LLM & RAG) (m/f/d)

At Machine Learning Reply, we help companies transform cutting-edge AI technologies into real-world applications and scalable digital products. Due to the expansion of our team, we are looking for a Junior AI Application Engineer who is passionate about developing AI solutions and intelligent product features using modern machine learning and generative AI technologies. While our GenAI engineers focus on developing AI models and architectures, AI Application Engineers focus on developing customer-centric AI applications and integrating AI capabilities into scalable products. In this role, you will work at the intersection of AI Engineering, Backend Development, Product Development, and Cloud Deployment, creating production-ready AI systems that deliver real business value.

Tasks As a Junior AI Application Engineer (m/f/d), you will design and develop AI-powered applications and product features for enterprise clients. Your tasks will include:

• Designing and developing AI applications such as enterprise assistants, copilots, semantic search platforms, and automation systems.
• Supporting the development of LLM-based solutions (including RAG) and comprehensive AI products by integrating APIs, enterprise data, and backend services.
• Building scalable AI microservices, APIs, as well as vector search, embedding, and retrieval systems.
• Rapid prototyping of AI features and their further development into production systems.
• Close collaboration with product managers, designers, AI engineers, and clients to develop effective solutions.
• Deploying AI systems in cloud and production environments using modern DevOps practices.
• Ensuring reliability, scalability, and observability through CI/CD, monitoring, and containerized deployments.

Benefits

• HYBRID WORK
• CORPORATE EVENTS
• EXPERT NETWORK
• CERTIFICATIONS
• Regular and systematic (external and internal) opportunities for further training in Generative AI, LLM development, cloud architecture, and Data Science.
• Work in an open, flat environment, as part of the broad Reply network for knowledge exchange.
• Award-winning office spaces in the center of Munich with access to the central line.
• Public transport ticket with Deutschlandticket.
• Co-financing of your sports activities through EGYM Wellpass and other Reply Group benefits.
• Flexible work environment between clients, Reply office, and remote work.

Requirements

• Completed higher education in Computer Science, Software Development, Data Science, or a similar technical field.
• Python programming skills and modern backend frameworks, as well as experience with AI, Machine Learning, and generative AI applications.
• Initial experience in developing scalable backend systems, APIs, and microservices, as well as knowledge of RAG, vector databases, and retrieval technologies.
• Hands-on experience in containerization and DevOps (e.g., Docker, CI/CD, Kubernetes), as well as deploying AI services in cloud environments (AWS, Azure, GCP).
• Experience with relevant frameworks (e.g., LangChain, LlamaIndex, Hugging Face).
• Knowledge in monitoring, observability, as well as evaluation and optimization of LLM systems.
• Very good knowledge of German and English for seminars and communication.

Examples of projects you could work on

• Enterprise AI Knowledge Assistants
• AI Copilots for internal business tools
• Semantic search platforms for enterprise data
• LLM-based Document Intelligence systems
• AI Agents and automation systems for corporate workflows