Back to board
Early applicant
Deutsche Telekom IT Solutions·Telecom·6 hours ago

AI SWE / Agentic SDLC Workflow Engineer - T Cloud Public (REF5735F)

Budapest, HungaryFull-timeMid · 2-5 yearsH1B likely

About this role

Company Description

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.

    Job Description

    Mission 
    Industrialize AI-assisted engineering workflows for Meridian by packaging repeatable patterns that support codebase intake, dependency extraction, build triage, documentation generation, and technical evidence creation across cloud software work packages. 

    Role focus 
    This position emphasizes reusable workflow engineering. The candidate should combine Python, APIs, orchestration frameworks, retrieval patterns, and AI development platforms to create governed workflows that can be reused across repositories, OpenStack-derived services, CI/CD outputs, architecture documentation, and handover evidence. 

    Key responsibilities 

    • Build reusable AI-assisted workflows for repository analysis, code scanning, service decomposition, dependency discovery, build diagnosis, and documentation generation. 

    • Package prompts, tools, retrieval layers, model routing, evaluation checks, retries, and human approval steps into repeatable engineering accelerators. 

    • Integrate AI workflows with Git platforms, CI/CD systems, documentation stores, issue trackers, test outputs, service catalogues, and architecture evidence repositories. 

    • Create workflow outputs that remain auditable, including traceable source references, confidence indicators, reviewer checkpoints, and explicit assumptions. 

    • Experiment with open-source, open-weight, and Chinese coding models in approved environments to compare usefulness for SDLC automation and handover tasks. 

    • Support work-package leads by translating ambiguous engineering questions into structured AI-assisted workflows and validated deliverables. 

    Examples of market tools, models, and SDLC platforms expected 

    • Agentic workflow frameworks such as LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, LlamaIndex Workflows, Semantic Kernel, or comparable orchestration stacks. 

    • AI development platforms and editor integrations such as Cursor, Windsurf, Claude Code, Continue, Cline, Aider, or VS Code-compatible internal assistants. 

    • Model families relevant to SDLC automation such as DeepSeek Coder, Qwen/Qwen-Coder, CodeGeeX, StarCoder, Code Llama, Mistral, or enterprise-hosted frontier models. 

    • Supporting components including vector databases, graph stores, code indexing, OpenAPI wrappers, GitLab/GitHub APIs, Jenkins APIs, observability, and evaluation dashboards. 

    Qualifications

    Candidate profile 

    • 5+ years of engineering experience across software development, DevOps automation, platform engineering, or AI workflow implementation. 

    • Strong hands-on Python skills, API integration experience, and practical knowledge of orchestration frameworks, RAG patterns, tool calling, and evaluation loops. 

    • Experience turning prototypes into reusable engineering workflows with clear interfaces, logging, error handling, configuration, and maintainability discipline. 

    • Good understanding of CI/CD, Git workflows, containers, Kubernetes, software architecture documentation, and modular cloud software environments. 

    • Strong written communication skills for creating workflow documentation, evidence packs, usage guidance, and decision support for senior stakeholders. 

    • Comfortable operating in ambiguous, confidentiality-sensitive settings where AI outputs must be reviewed, justified, and converted into reliable engineering evidence. 

    Additional Information

    Please note: remote working is only possible from within Hungary due to European taxation regulations.

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