AI SWE / Agentic Handover Engineer (m/f/d)

## Company Description T‑Systems is part of the Deutsche Telekom Group, with around 30.000 employees worldwide. We create technology with purpose to generate a positive impact on society. We are looking for curious talent, eager to learn, take on challenges, and contribute ideas that transform our customers’ experience. We trust people: we offer autonomy, continuous support, and a collaborative environment where you can grow without limits. We are one global team, guided by respect, integrity, and a passion for doing better every day. ## Job Description **Mission** Deliver AI-assisted handover and due diligence support with added emphasis on automation, repeatability, evidence generation, and reusable workflow packaging across multiple engineering work packages. A central goal of the role is to create repeatable AI-assisted workflows that help assess, document, and transition a cloud software stack derived from OpenStack. **Role focus** This second position complements Position A by emphasizing workflow engineering so that AI-assisted code understanding can be reused consistently across repositories, teams, and technical assessment tasks. The role should help industrialize analysis of modular cloud software environments based on OpenStack-style architecture and related CI/CD and integration flows. **Key responsibilities** - Build reusable AI-assisted workflows for repository intake, code scanning, dependency extraction, build issue triage, and documentation generation. - Package prompts, retrieval steps, tool integrations, and evaluation logic into repeatable engineering patterns suitable for enterprise delivery. - Create workflow accelerators that support the analysis and handover of a cloud software stack derived from OpenStack, including service mapping, control-plane understanding, and cross-component dependency views. - Help define quality gates for AI-assisted outputs, including traceability, explainability, approval points, and human-in-the-loop controls. - Partner with technical PMO and work-package leads to produce evidence packs that support decisions, risks, and transition readiness views. - Improve throughput of technical due diligence activities without compromising engineering quality, auditability, or confidentiality constraints.[ **Examples of market tools and workflow frameworks expected** - Agentic workflow frameworks such as LangGraph, OpenAI Agents SDK, AutoGen, CrewAI, LlamaIndex Workflows, or similar orchestration stacks. - Tool integration and agent control patterns such as memory, tool calling, structured retries, fallback logic, evaluation loops, and human-in-the-loop review stages. - Supporting components such as vector databases, retrieval layers, observability tooling, and API/service wrappers that allow workflows to operate across code, documents, and engineering evidence. - Engineering workflows that can operate across OpenStack-related repositories, CI/CD systems, architecture metadata, test outputs, and service dependency graphs are especially relevant. ## Qualifications - 5+ years of engineering experience with strong delivery discipline and comfort operating across software, DevOps, and documentation boundaries. - Hands-on background in Python, APIs, orchestration frameworks, and developer tooling. - Practical experience with AI systems in production, especially RAG, evaluation pipelines, tool use, prompt workflows, and observability. - Strong written communication skills for producing concise engineering evidence and handover outputs for senior stakeholders. - Ability to work in ambiguous environments and translate partial technical evidence into structured findings and recommendations. - Familiarity with modular cloud software stacks derived from OpenStack, or similarly complex multi-service infrastructure platforms, is strongly preferred. ## Additional Information **What do we offer you?** **Work environment & flexibility** - International, dynamic and collaborative environment. - T-Social…