As an LLM Application Engineer / Senior Software Engineer, you will play a central role in our development team. You will be responsible for independently building the shared LLM platform – from proof of concept to production – and will oversee two tracks: internal tools and customer products. Your focus will be on application building using foundation models: RAG, agents, LangChain/LlamaIndex, orchestration, prompt engineering, and product integration.

• LLM platform layer structure: Retrieval backend, embedding pipeline, API design
• Integration of LLM APIs (OpenAI, Anthropic, Mistral, etc.) into internal and customer systems
• Development of AI features: Conversational Analyst, semantic search, intelligent alert feed
• Implementation of agent architectures and MCP interfaces for enterprise connectivity
• Contributing to the development of prototypes and proof-of-concepts for new AI use cases

profile

• Graduates of computer science, business informatics, data science or a related field of study
• Experience with
  • RAG pipelines in production — Vector DB, retrieval, chunking, evaluation/grounding
  • LLM frameworks — LangChain / LlamaIndex (or similar) for orchestration, chains/agents, tool use
  • LLM application engineering — prompt/context engineering, function calling, agent architectures
  • Backend — Node/Python (or similar), clean services, async, API design, data modeling
  • Frontend — React / TypeScript, builds usable user interfaces for the AI ​​features itself
  • Data pipelines — ingestion, normalization, embedding via structured and semi-structured sources
  • MCP (Model Context Protocol)
• Passionate handling of AI-native interfaces
•