We are a research-driven spin-off building an on-premise AI platform that enables organizations to securely leverage their internal knowledge (documents, workflows, internal data) with full access control and auditability.
Your Role
As a key member of our team, you will:
- Develop backend APIs for data ingestion, search/retrieval, and system integrations
- Build and integrate LLM inference endpoints and RAG (Retrieval-Augmented Generation) pipelines
- Contribute to a web UI for system configuration and review/approval workflows
- Work hands-on with state-of-the-art AI technologies and open-source tools
- Help prepare and deploy pilot projects for early customers
Core Technical Skills
Backend
- Python (preferably FastAPI)
- PostgreSQL (SQL, data modeling)
- REST APIs
- Linux basics
Frontend
- React (TypeScript preferred)
- Node.js ecosystem
Nice to Have (Not Required)
- Vector search / retrieval (e.g. pgvector)
- LLM integration (OpenAI-compatible APIs, vLLM, Ollama)
- Document processing (e.g. Apache Tika)
- Docker / CI/CD
- Security basics (OIDC, TLS, secrets handling)
- Familiarity with the Model Context Protocol (MCP)