Das machst du bei uns:
You’ll be the driving force behind a production-ready, fully asynchronous FastAPI-based RAG (Retrieval-Augmented Generation) system that powers personalized e-learning experiences.
This role is perfect for someone who loves to design AI architecture and get their hands dirty building and deploying it — taking things from idea to “running on the big machine.”
You’ll own the full lifecycle: from architecture and implementation to deployment, monitoring, and continuous improvement.
Expect to work closely with product and engineering teams where research meets production — building things that actually ship, scale, and make a difference.
What you’ll do
This role is perfect for someone who loves to design AI architecture and get their hands dirty building and deploying it — taking things from idea to “running on the big machine.”
You’ll own the full lifecycle: from architecture and implementation to deployment, monitoring, and continuous improvement.
Expect to work closely with product and engineering teams where research meets production — building things that actually ship, scale, and make a difference.
What you’ll do
- Develop and maintain a fully asynchronous FastAPI backend for AI services
- Build and scale a RAG pipeline using Qdrant (vector search) and PostgreSQL (metadata)
- Design modular, scalable NLP and LLM architectures — from embedding pipelines to agent orchestration
- Create APIs that connect frontends with AI systems and make data flow seamlessly
- Deploy and monitor using Docker, Kubernetes, Prometheus, and Grafana
- Collaborate across teams to translate ideas into reliable, high-performing systems