AI DevOps Engineer (f/m/d)
osapiens
About the role
About
We’re looking for an AI Development Operations Engineer to build and operate the internal AI infrastructure that empowers our developers to work smarter and ship faster. You will integrate cutting‑edge AI systems like Claude, Codex and next‑generation agentic frameworks directly into engineering workflows, making AI a natural part of how we design, build and maintain software.
Why This Role Matters
AI assisted development is reshaping modern engineering. In this role, you’ll architect and run our core AI developer platform, from ingestion pipelines and vector search to context assembly, RAG systems and agent skill libraries. You’ll embed AI seamlessly into IDEs, CI/CD pipelines, code reviews and architectural decisions, enabling teams to tackle tasks like refactoring, debugging, test generation and security scanning with powerful agentic capabilities. At the same time, you will ensure that the platform operates securely, reliably, and responsibly. Your work defines how quickly—and how well—our engineers build the next generation of our product.
Responsibilities
- Design and operate our end‑to‑end AI platform (RAG pipelines, retrieval, indexing, embeddings, vector DBs).
- Build MCP Servers, extensions and integrations for IDEs, CI/CD systems and internal tooling.
- Create orchestration interfaces that allow AI agents to interact safely with internal systems.
- Develop reusable agent skills for architecture reasoning, secure coding, test generation, debugging and more.
- Maintain and evolve a skill library aligned with engineering needs and platform adoption.
- Automate code review, CI checks and troubleshooting with LLM‑based workflows.
- Provide context‑aware knowledge retrieval across codebases, logs, docs, incidents and design artifacts.
- Define guidelines for prompt engineering, model evaluation and cost optimization.
- Implement monitoring, audit logging, performance tracking and access controls.
- Partner closely with engineering, product and QA teams.
- Communicate platform strategy and progress to leadership.
- Support developers in adopting and maximizing AI‑based workflows.
Experience
- Design and operate an end‑to‑end AI platform (RAG pipelines, retrieval, indexing, embeddings, vector DBs).
- Build MCP Servers, extensions and integrations for IDEs, CI/CD systems and internal tooling.
- Create orchestration interfaces that allow AI agents to interact safely with internal systems.
- Develop reusable agent skills for architecture reasoning, secure coding, test generation, debugging and more.
- Maintain and evolve a skill library aligned with engineering needs and platform adoption.
- Automate code review, CI checks and troubleshooting with LLM‑based workflows.
- Provide context‑aware knowledge retrieval across codebases, logs, docs, incidents and design artifacts.
- Define guidelines for prompt engineering, model evaluation and cost optimization.
- Implement monitoring, audit logging, performance tracking and access controls.
- Partner closely with engineering, product and QA teams.
- Communicate platform strategy and progress to leadership.
- Support developers in adopting and maximizing AI‑based workflows.
Benefits
- A purpose‑driven mission tackling complex sustainability challenges while working alongside global industry pioneers at a fast‑growing unicorn company
- Room for creativity through collaborative teamwork and an open communication culture
- Flexibility and team bonding with our hybrid work options
- Fuel for your growth journey, both personally and professionally
- Sustainable mobility options, promoting eco‑friendly commuting solutions
- Fun team events and outings with our global teams
- Inspiring workspaces in Mannheim, Munich and Madrid
Salary
EUR 43,200 – 84,000 per year
Job ID
#J-18808-Ljbffr
Requirements
- Design and operate an end-to-end AI platform (RAG pipelines, retrieval, indexing, embeddings, vector DBs).
- Build MCP Servers, extensions and integrations for IDEs, CI/CD systems and internal tooling.
- Create orchestration interfaces that allow AI agents to interact safely with internal systems.
- Develop reusable agent skills for architecture reasoning, secure coding, test generation, debugging and more.
- Maintain and evolve a skill library aligned with engineering needs and platform adoption.
- Automate code review, CI checks and troubleshooting with LLM-based workflows.
- Provide context aware knowledge retrieval across codebases, logs, docs, incidents and design artifacts.
- Define guidelines for prompt engineering, model evaluation and cost optimization.
- Implement monitoring, audit logging, performance tracking and access controls.
- Partner closely with engineering, product and QA teams.
- Communicate platform strategy and progress to leadership.
- Support developers in adopting and maximizing AI based workflows.
Responsibilities
- Design and operate our end-to-end AI platform (RAG pipelines, retrieval, indexing, embeddings, vector DBs).
- Build MCP Servers, extensions and integrations for IDEs, CI/CD systems and internal tooling.
- Create orchestration interfaces that allow AI agents to interact safely with internal systems.
- Develop reusable agent skills for architecture reasoning, secure coding, test generation, debugging and more.
- Maintain and evolve a skill library aligned with engineering needs and platform adoption.
- Automate code review, CI checks and troubleshooting with LLM-based workflows.
- Provide context aware knowledge retrieval across codebases, logs, docs, incidents and design artifacts.
- Define guidelines for prompt engineering, model evaluation and cost optimization.
- Implement monitoring, audit logging, performance tracking and access controls.
- Partner closely with engineering, product and QA teams.
- Communicate platform strategy and progress to leadership.
- Support developers in adopting and maximizing AI based workflows.
Benefits
Skills
Don't send a generic resume
Paste this job description into Mimi and get a resume tailored to exactly what the hiring team is looking for.
Get started free