AI Platform Engineer for AI and LLM Applications (Freelancer)

Project overview

For a client project, we are looking for an experienced AI Platform Engineer to develop and integrate a platform for AI and LLM applications. The focus is on asynchronous Python services with FastAPI, LLM gateways, MCP, Qdrant, and secure integration via OAuth2.

Responsibilities

• Development of asynchronous backend services and APIs with Python and FastAPI
• Integration and connection of LLM gateways
• Development and integration of MCP servers and MCP clients
• Connection and use of Qdrant for vector search and retrieval
• Implementation of authentication and authorization with OAuth2
• Integration of the platform into existing applications and systems
• Ensuring maintainability, reliability, and security of the services
• Technical documentation and coordination with the development team

Requirements

Framework Conditions

Search terms: AI Platform Engineer, Python, Async Python, FastAPI, LLM Gateway, MCP, Model Context Protocol, Qdrant, OAuth2, API, Generative AI

Please send your current profile/CV in Word format with details on your availability and hourly rate (remote).

• Several years of practical experience with Python, especially asynchronous development
• Sound knowledge of FastAPI and API design
• Experience with LLM gateways and the integration of LLM services
• Project experience with MCP (Model Context Protocol)
• Experience with Qdrant or a comparable vector database
• Knowledge of OAuth2 and secure API authentication
• Independent, structured way of working and good communication skills
• Start: by agreement
• Duration: 6 months
• Workload: by agreement
• Location: remote / by agreement
• Contract type: freelance work

Project details

• Start: 2026-12
• Duration: 6 Monate
• Remote: hybrid
• Location: Remote, Deutschland, DE
• Languages: German