Head of AI Engineering (m/w/d) - Schwerpunkt: Agentic Systems & Backend Engineering (IT-Projektkoordinator/in)

Germany | Oct. 15, 2026

Report as Closed

Company: conmeet GmbH

Country: Germany

Type: Hybrid remote

Employment: Full-time

Description: Your role

You take on technical and professional responsibility for our AI systems - from the agent-based assistant to a platform on which our customers can put together their own agents, tasks and processes.

This is deliberately not a pure management role: you work hands-on on the code, make architectural decisions and, in parallel, build the structures, standards and - in the future - the team with which we scale our AI products. You are the person who ensures that promising prototypes become reliable, measurable and safe production systems.

Our team and your opportunity

small 25 employeesLocations: 2Software development

A young, dynamic team awaits you at conmeet, working with passion and expertise on the future of digital craftsmanship. We maintain a relaxed atmosphere in which fun at work is not neglected, without losing sight of our ambitious goals. Teamwork is very important to us: We support each other, share knowledge and celebrate our successes together.

We believe in the continuous development of our team members. That’s why we encourage and challenge you in equal measure. You get the opportunity to grow with complex, challenging tasks and take your skills to the next level. Regardless of whether it is about solving technical problems, developing onboarding processes or building customer knowledge - with us you will always find new challenges that will advance you as a customer success professional.

Your main tasks

(Further) development of our agent-based AI assistant - from conception to implementation to operation

- Building a dynamic multi-agent system in which customers create their own agents, tasks and workflows themselves and configure
- Design of agent systems whose behavior and quality are controllable and comprehensible - including guardrails, authorization concepts and human-in-the-loop mechanisms
- Development of systematic evaluation strategies: You define how we measure quality and ensure that changes to prompts, tools and agents are verifiable instead of just "feeling better"
- Integration of AI and ML concepts into an existing, grown SaaS application - with everything that goes with it: data model, authorizations, performance, costs
- Technical leadership: architectural decisions, code reviews, technical sparring partner for product and engineering, development of best practices
- Operation and optimization: observability, tracing, latency, cost and stability optimization

Your profile

LLM and ML understanding

- Very good conceptual understanding of how it works and the Limits of LLMs
- Understanding of other ML concepts and how these can be meaningfully integrated into business logic

In-depth understanding of:

- Tokenization/tokens, embeddings and context windows
- Vector search, retrieval and re-ranking (RAG)
- Hallucinations, context bloat and other typical error modes - including strategies to recognize and mitigate these
- Tool calling and structured Outputs
- A2A (Agent2Agent Protocol), MCP (Model Context Protocol) and Human-in-the-Loop
- Security risks of LLM and agent systems (including prompt injection, tool misuse, data leakage)
- Prompt Engineering – formulation, structure and control of individual model requests
- Context Engineering – targeted selection, preparation and management of what at all

Techstack

This is how we work. What is written in bold is our stack - what is next to it shows that we also take experience with comparable technologies into account. Experience with as many of these points as possible is an advantage, but we do not expect the complete list:

LLM / AI: Anthropic API – Anthropic Client, Anthropic on Vertex AI (or experience with comparable LLM clients and APIs)

ML toolchain: Toolchain for developing and evaluating your own ML applications, e.g. B. PyTorch, TensorFlow, scikit-learn, NumPy, pandas, CUDA

Cloud: Google Cloud Platform – Vertex AI, Cloud Run, GKE (or comparable platforms such as AWS or Azure)

Infrastructure: Kubernetes, Docker

Backend: Python, Django

Database: PostgreSQL (or a comparable RDBMS)

Async / Jobs: Celery, Taskiq or comparable worker-based task queue systems

Other: Git

This is what we offer

- Design freedom in an area where no one has ready answers yet - you shape the architecture and standards from the ground up
- A product with real users and real feedback instead Innovation Theater
- Work remotely/hybrid, or on site
- Structured familiarization with products, processes and testing procedures
- And of course all the other basics that everyone now has on their career page...;-)

Home office:
Scope: By arrangement

Apply here:

Web: Apply here

Emails: