Job Description

Key responsibilities Implement and maintain small AI-assisted engineering utilities for repository indexing, code summarization, dependency extraction, log parsing, and documentation generation. Support senior engineers in configuring AI development environments, testing prompts, comparing model outputs, and documenting repeatable SDLC usage patterns. Create scripts and lightweight services that connect Git repositories, CI/CD logs, issue trackers, documentation stores, and internal model endpoints. Help prepare handover materials including codebase summaries, service notes, build observations, glossary entries, and structured evidence templates. Test open-source, open-weight, and Chinese coding models in approved environments and document strengths, limitations, risks, and practical usage guidance. Participate in reviews with senior engineers to validate AI-generated outputs, correct inaccuracies, and improve workflow quality over time. Examples of market tools, models, and SDLC platforms expected AI development environments such as Cursor, Windsurf, Continue, Cline, Aider, Claude Code, or VS Code-based extensions configured for enterprise repositories. Model families used for coding support such as DeepSeek Coder, Qwen/Qwen-Coder, CodeGeeX, StarCoder, Code Llama, Mistral, or other internally approved models. Workflow and integration tooling such as Python, FastAPI, notebooks, LangChain, LlamaIndex, GitLab/GitHub APIs, Jenkins APIs, Markdown, and documentation automation. Supporting engineering tools such as Git, Docker, Kubernetes basics, Helm basics, Linux shells, package managers, log processing, and structured prompt repositories.

Qualifications

2-4 years in software engineering, DevOps automation, data engineering, AI tooling, or platform-adjacent development roles. Good Python skills and willingness to work across APIs, scripting, developer tooling, documentation, tests, and lightweight automation services. Hands-on familiarity with AI coding assistants, prompt engineering, LLM APIs, local model experimentation, or RAG-style development is strongly preferred. Basic understanding of Git, CI/CD, Linux, containers, cloud platforms, and software architecture documentation, with readiness to deepen OpenStack knowledge. Careful working style with good documentation habits, curiosity, and ability to escalate unclear findings instead of over-trusting AI-generated answers. Comfortable working in a confidential enterprise environment where learning speed, quality discipline, and structured communication are important. Additional Information What do we offer you? Work environment & flexibility International, dynamic and collaborative environment. T-Social: social initiatives (sports, community, health, ...). Hybrid work model (remote/on-site). Flexible working hours. Growth & development Customized training: access to Coursera to learn whatever you want, whenever you want. Weekly language classes (English & German). International Mentoring Sessions & Experience Days. Compensation & benefits Flexible compensation plan (health insurance, meal vouchers, childcare, transport). Telemedicine. Life and accident insurance. Social fund. Wellbeing & time off 26+ working days of vacation per year. Free access to specialists services (medical, legal, wellness). 100% salary coverage during medical leave. And many more advantages of being part of T-Systems! If you are looking for a new challenge, do not hesitate to send us your CV! Please send CV in English. Join our team! T-Systems Iberia will only process the CVs of candidates who meet the requirements specified for each offer.

Your Task

This role focuses on implementing and maintaining small AI-assisted engineering utilities and supporting senior engineers in AI development workflows. You will work with repository indexing, code summarization, dependency extraction, log parsing, and documentation generation tools.

Key Responsibilities

• Implement and maintain small AI-assisted engineering utilities for repository indexing, code summarization, dependency extraction, log parsing, and documentation generation

• Support senior engineers in configuring AI development environments, testing prompts, comparing model outputs, and documenting repeatable SDLC usage patterns

• Create scripts and lightweight services that connect Git repositories, CI/CD logs, issue trackers, documentation stores, and internal model endpoints

• Help prepare handover materials including codebase summaries, service notes, build observations, glossary entries, and structured evidence templates

• Test open-source, open-weight, and Chinese coding models in approved environments and document strengths, limitations, risks, and practical usage guidance

• Participate in reviews with senior engineers to validate AI-generated outputs, correct inaccuracies, and improve workflow quality over time

Tools and Platforms

You will work with AI development environments such as Cursor, Windsurf, Continue, Cline, Aider, Claude Code, or VS Code-based extensions configured for enterprise repositories. The role involves using model families for coding support such as DeepSeek Coder, Qwen/Qwen-Coder, CodeGeeX, StarCoder, Code Llama, Mistral, or other internally approved models. You will utilize workflow and integration tooling such as Python, FastAPI, notebooks, LangChain, LlamaIndex, GitLab/GitHub APIs, Jenkins APIs, Markdown, and documentation automation, along with supporting engineering tools such as Git, Docker, Kubernetes basics, Helm basics, Linux shells, package managers, log processing, and structured prompt repositories.

Your Profile

We are seeking an AI-Assisted Engineering Support Engineer with strong Python development skills, hands-on experience with AI coding assistants, and solid understanding of software development lifecycle tools and practices in an enterprise environment.

Must Have Skills

• 2-4 years of experience in software engineering, DevOps automation, data engineering, AI tooling, or platform-adjacent development roles

• Strong Python skills with ability to work across APIs, scripting, developer tooling, documentation, tests, and lightweight automation services

• Basic understanding of Git version control

• Basic understanding of CI/CD pipelines

• Basic understanding of Linux operating systems

• Basic understanding of containers (Docker)

• Basic understanding of cloud platforms

• Basic understanding of software architecture documentation

• Readiness to deepen OpenStack knowledge

• Careful working style with good documentation habits

• Curiosity and willingness to learn

• Ability to escalate unclear findings instead of over-trusting AI-generated answers

• Comfortable working in a confidential enterprise environment

• Learning speed and quality discipline

• Structured communication skills

Nice to Have Skills

• Hands-on familiarity with AI coding assistants (such as Cursor, Windsurf, Continue, Cline, Aider, Claude Code, or VS Code-based extensions)

• Experience with prompt engineering

• Experience with LLM APIs

• Experience with local model experimentation

• Experience with RAG-style development

• Familiarity with AI development environments configured for enterprise repositories

• Experience with model families used for coding support (DeepSeek Coder, Qwen/Qwen-Coder, CodeGeeX, StarCoder, Code Llama, Mistral, or other internally approved models)

• Experience with FastAPI

• Experience with Jupyter notebooks

• Experience with LangChain

• Experience with LlamaIndex

• Experience with GitLab/GitHub APIs

• Experience with Jenkins APIs

• Experience with Markdown

• Experience with documentation automation

• Experience with Kubernetes basics

• Experience with Helm basics

• Experience with Linux shells

• Experience with package managers

• Experience with log processing

• Experience with structured prompt repositories