Sovereign AI Plattform Engineer (m/w/d/x)
Deutsche Telekom
- Location
- Hybrid (Weingarten, BW,DE · Berlin, BE,DE · BN, NRW,DE · Leinfelden-Echterdingen, BW,DE · Munich, BY,DE · +2 more)
- Employment
- Full-time
- Level
- Senior Level
Posted 3 days ago
About the Role
T-Systems International is seeking a Platform Engineer to develop and operate a secure, high-performance AI toolchain and Kubernetes-based platform for isolated IT environments. The role focuses on ensuring data sovereignty, security, and compliance while managing model-serving solutions and infrastructure.
Skills
Kubernetes
Linux
Python
Terraform
Ansible
Helm
GitOps
MLOps
LLM
GPU optimization
Vector databases
Qdrant
Argo CD
Infrastructure as Code
Data sovereignty
IT security
Benefits
- Health promotion
- Company pension scheme
- Employee discounts
- Public transport ticket
Perks
- Flexible working hours
- Remote work options
- Hybrid working model
Full job details
About T-Systems International GmbH
At T-Systems, we provide our business customers with the right system solutions for their digital business. With our portfolio, we ensure that digital transformation reduces complexity, lowers costs, and makes everyday work easier. Our focus areas are Connectivity, Digital, Cloud & Infrastructure, and Security – Let's power higher performance!
About the Position
As a Platform Engineer with a focus on Sovereign AI, you will develop, implement, and operate a secure and high-performance AI toolchain for use in isolated or particularly protected IT environments.
You will design Kubernetes-based platforms for AI inference, retrieval, experimentation, and agent-based applications. In doing so, you will integrate and operate open-source and open-weight models, model-serving solutions, model gateways, vector databases, as well as internal user interfaces and APIs.
Using Infrastructure as Code, GitOps, and automated deployment processes, you will create stable, reproducible, and auditable platform environments. You will manage private registries, local package and model repositories, secrets, access permissions, storage, network components, and observability solutions in environments with restricted or completely disconnected access to public cloud services.
You will also optimize GPU, CPU, storage, and network resources for reliable AI workloads and ensure compliance with security, audit, and data sovereignty requirements.
Must-Have Skills
- At least five years of experience in Platform Engineering, DevOps, Site Reliability Engineering, or MLOps
- Very good knowledge of Kubernetes and Linux
- Experience with AI infrastructure, model serving, and LLM-based applications
- Experience with private, on-premises, or isolated deployment environments
- Good knowledge of Python, Terraform, Ansible, Helm, and GitOps
- Strong knowledge of networking, storage, access control, and monitoring
- Experience with GPU-enabled platforms and the optimization of AI workloads
- Very good understanding of IT security, data sovereignty, and auditable operating models
- Very good written and spoken German skills at C1 level
- Experience with vLLM, Ollama, llama.cpp, or comparable model-serving solutions
- Knowledge of working with open-source or open-weight models
- Experience with vector databases such as Qdrant and Retrieval-Augmented Generation
- Knowledge of Argo CD, private registries, and local package or model repositories
- Experience with Open WebUI or comparable internal AI interfaces
- Knowledge of GPU scheduling, LLMOps, observability, and air-gapped environments
- Experience with VS Code-compatible integrations and internal AI interfaces
What You Can Expect
You will help shape a sovereign AI platform for the secure operation of modern Large Language Models in isolated and particularly protected IT environments.
You will work with Kubernetes, open-source and open-weight models, GPU-enabled infrastructure, model serving, retrieval, GitOps, and Infrastructure as Code. You will create stable, reproducible, and auditable platforms and make an important contribution to data sovereignty, security, and technological independence.
What We Offer
Flexibility and work-life balance: Benefit from flexible working hours, the option to work remotely, and a hybrid working model.
Attractive compensation: A competitive salary package that recognizes your expertise and performance.
Development opportunities: Access to extensive learning opportunities, training programs, and career development initiatives.
Modern working environment: Work with modern equipment and the latest technologies and tools.
Strong corporate culture: An open and collaborative working environment in which teamwork and mutual support are highly valued.
Health and well-being: Health promotion programs and initiatives that support your well-being.
Additional benefits: Various benefits, including a company pension scheme, employee discounts, and public transport ticket options.
Your application may be processed by external service providers in Germany. Applications for positions outside Deutsche Telekom AG may also be processed by recruiters in other European countries. This also applies to the processing of applications at subsidiaries of Deutsche Telekom AG. The following information therefore applies to our civil servants: You are not required to include documents relevant to your personnel file with your application, particularly official performance evaluations. You are, of course, welcome to submit these documents voluntarily.
This position is also available on a part-time basis.
People with disabilities will be given priority in cases of equal suitability.