> Markdown version of [/jobs/ext/4254731-ai-software-engineer-agentic-sdlc-workflow-engineer](https://www.wearedevelopers.com/jobs/ext/4254731-ai-software-engineer-agentic-sdlc-workflow-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# AI Software Engineer / Agentic SDLC Workflow Engineer

- **Company:** T-mobile
- **Location:** A Coruña, Spain
- **Contract:** Permanent contract
- **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Cloud Computing, Code Review, Continuous Integration, Cursor, Decision Support Systems, Github, Python (Programming Language), Open Source Technology, Software Architecture, Systems Development Life Cycle, OpenAI, Software Engineering, Systems Integration, Openapi, Data Logging, Cloud Platform System, Retrieval-Augmented Generation, Claude Code, Qwen, Llamaindex, Indexer, Agentic-AI, Gitlab, Git, Git Flow, Kubernetes, Deployment Automation, CrewAI, AutoGen, Semantic Kernel, Automation Anywhere, Deepseek (AI Talent Sourcing Platform), Jenkins
- **Published:** October 16, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=3cb9b2cf497fea88

## About the Role

We are seeking an experienced AI Workflow Engineer with extensive engineering experience across software development, DevOps automation, and AI workflow implementation. The ideal candidate should have strong Python skills, hands-on experience with agentic workflow frameworks, and deep understanding of CI/CD systems and cloud environments., * 5+ years of engineering experience across software development, DevOps automation, platform engineering, or AI workflow implementation

 * Strong hands-on Python skills
 * API integration experience
 * Practical knowledge of orchestration frameworks
 * Practical knowledge of RAG patterns
 * Practical knowledge of tool calling
 * Practical knowledge of evaluation loops
 * Experience turning prototypes into reusable engineering workflows with clear interfaces, logging, error handling, configuration, and maintainability discipline
 * Good understanding of CI/CD
 * Good understanding of Git workflows
 * Good understanding of containers
 * Good understanding of Kubernetes
 * Good understanding of software architecture documentation
 * Good understanding of 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
 * Experience with agentic workflow frameworks such as LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, LlamaIndex Workflows, Semantic Kernel, or comparable orchestration stacks
 * Experience with AI development platforms and editor integrations such as Cursor, Windsurf, Claude Code, Continue, Cline, Aider, or VS Code-compatible internal assistants
 * Knowledge of model families relevant to SDLC automation such as DeepSeek Coder, Qwen/Qwen-Coder, CodeGeeX, StarCoder, Code Llama, Mistral, or enterprise-hosted frontier models
 * Experience with supporting components including vector databases, graph stores, code indexing, OpenAPI wrappers, GitLab/GitHub APIs, Jenkins APIs, observability, and evaluation dashboards

## Description

This role focuses on building reusable AI-assisted workflows for repository analysis, code scanning, service decomposition, dependency discovery, build diagnosis, and documentation generation. You will package prompts, tools, retrieval layers, model routing, evaluation checks, retries, and human approval steps into repeatable engineering accelerators., * 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, * Customized training: access to Coursera to learn whatever you want, whenever you want
 * Weekly language classes (English & German)
 * International Mentoring Sessions & Experience Days