Über die Stelle
Lead AI Engineer (Python / LLM / Agentic AI)
Job Description
We are looking for an experienced Lead AI Engineer to design, develop, and deliver production-ready AI applications and backend services.
The ideal candidate combines strong Python backend engineering skills with hands-on experience building LLM-powered applications, AI agents, and intelligent automation solutions.
Key Responsibilities
- Design, develop, and maintain scalable backend services and AI-powered applications using Python.
- Design and implement AI agents and agentic workflows, including tool calling, orchestration, multi-step reasoning, and multi-agent collaboration.
- Build LLM-powered solutions using RAG, embeddings, vector databases, and structured outputs.
- Integrate LLMs with internal systems, enterprise APIs, and external services using MCP and other integration approaches.
- Evaluate and optimize AI solutions for accuracy, reliability, performance, latency, and cost.
- Design scalable architectures using asynchronous processing, message queues, caching, and event-driven patterns.
- Implement AI security controls, including prompt injection protection, data privacy, access control, and safe tool execution.
- Build and deploy production-ready services with proper testing, monitoring, logging, and error handling.
- Collaborate with product and engineering teams to translate business requirements into technical solutions.
- Lead technical design discussions, review code, mentor engineers, and establish engineering best practices.
Requirements
Job Requirements
Required Qualifications
- 7+ years of professional software engineering experience, including at least 2 years of backend development using Python.
- Strong experience with Python, FastAPI, asynchronous programming, and Pydantic.
- Hands-on experience developing and deploying LLM-powered applications in production.
- Practical experience with AI agents, tool/function calling, and agent orchestration frameworks, such as LangGraph, LangChain, or equivalent solutions.
- Strong understanding of RAG architectures, embeddings, semantic search, and vector databases.
- Experience integrating LLMs through APIs, including structured outputs, prompt engineering, and handling model failures.
- Experience evaluating LLM applications, including response quality, hallucinations, reliability, and performance.
- Solid understanding of distributed systems, message queues, caching, retries, idempotency, and persistent state management.
- Experience with PostgreSQL, Redis, Docker, and REST APIs.
- Strong knowledge of automated testing, clean architecture, design patterns, and code quality practices.
- Experience designing and delivering major features or products from concept to production.
- Strong analytical, troubleshooting, communication, and technical leadership skills.
- Experience with Model Context Protocol (MCP) and building MCP servers or clients.
- Experience with advanced agent orchestration, multi-agent architectures, and human-in-the-loop workflows.
- Experience with Qdrant, pgvector, Pinecone, or similar vector databases.
- Experience with NATS, Kafka, or other event-driven messaging technologies.