Senior AI Platform Engineer – T Cloud Public (REF5735F)

As Hungary’s most attractive employer in 2025 (according to Randstad’s representative survey), Deutsche Telekom IT Solutions is a subsidiary of the Deutsche Telekom Group. The company provides a wide portfolio of IT and telecommunications services with more than 5300 employees. We have hundreds of large customers, corporations in Germany and in other European countries.

DT-ITS recieved the Best in Educational Cooperation award from HIPA in 2019, acknowledged as the the Most Ethical Multinational Company in 2019. The company continuously develops its four sites in Budapest, Debrecen, Pécs and Szeged and is looking for skilled IT professionals to join its team.

We are looking for a Senior AI Platform Engineer to build AI-powered automation for complex cloud engineering environments.

You will combine your platform engineering, software development and cloud expertise with modern Generative AI technologies to automate parts of the software development lifecycle (SDLC).

Your work will focus on building reusable AI-assisted workflows that help engineering teams understand large codebases, discover service dependencies, diagnose CI/CD failures, analyze cloud services and generate reliable technical documentation.

This is not a traditional data science or machine learning role. We are looking for an engineer who understands how modern software and cloud platforms work and can apply LLMs, RAG and AI agents to real engineering problems.

What you'll work on

You will design and build AI-powered engineering workflows such as:

• Analyzing large Git repositories and identifying service boundaries and dependencies
• Building AI agents that interact with source code, Git platforms, CI/CD systems and engineering tools
• Diagnosing build and deployment failures using source code, configuration and pipeline logs
• Creating RAG-based solutions for searching and understanding large codebases and technical documentation
• Automating the generation of architecture and engineering documentation
• Connecting LLMs to engineering systems through APIs and tool calling
• Building controlled agentic workflows with validation, retries, confidence checks and human approval steps
• Evaluating different LLMs and approaches for software engineering use cases
• Turning successful prototypes into reusable, maintainable and production-ready engineering solutions

You will work closely with cloud, platform and software engineers within the T Cloud Public / Meridian engineering environment.

Your core experience

• Several years of professional experience in Platform Engineering, DevOps, Site Reliability Engineering, Cloud Engineering or software engineering in cloud-native environments
• Strong programming and automation skills, preferably in Python
• Hands-on experience with Kubernetes, containers and cloud-native architectures
• Good understanding of Git-based development workflows and CI/CD systems such as GitLab CI, Jenkins, GitHub Actions or similar
• Experience integrating systems through REST APIs, SDKs and automation
• Strong understanding of how modern distributed applications and cloud services are built, deployed and operated
• Hands-on experience building or integrating Generative AI / LLM-based applications

AI experience

You do not need to be a machine learning researcher.

We are looking for practical experience applying AI to engineering problems, ideally including some of the following:

• RAG (Retrieval-Augmented Generation) and semantic/vector search
• LLM tool calling and integration with external systems
• AI agents and multi-step agentic workflows
• Agent frameworks such as LangGraph, AutoGen, CrewAI, Semantic Kernel, OpenAI Agents SDK or comparable technologies
• LLM evaluation, observability and quality validation
• AI-assisted source-code analysis or developer tooling

Experience with one framework or model is more important than experience with a specific technology from this list.

Nice to have

Experience in any of the following would be an advantage:

• OpenStack or other large-scale cloud platforms
• Infrastructure as Code such as Terraform or Ansible
• GitOps and platform engineering practices
• Vector databases such as pgvector, Qdrant, Weaviate, Milvus or similar
• LlamaIndex or comparable retrieval/indexing technologies
• Developer productivity or internal developer platform tooling
• Working with large or unfamiliar software repositories
• Software architecture analysis and service decomposition
• Technical due diligence, software transition or engineering handover projects
• Operating software in security- or sovereignty-sensitive environments

* Please be informed that our remote working possibility is only available within Hungary due to European taxation regulation.