> Markdown version of [/jobs/ext/3646274-senior-devops-engineer](https://www.wearedevelopers.com/jobs/ext/3646274-senior-devops-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).

---

# Senior DevOps Engineer

- **Company:** welevel GmbH
- **Location:** München, Germany
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Bash Shell, Cloud Computing, Linux, DevOps, Python (Programming Language), Language Modeling, Large Language Models, Backend, Deployment Automation, Performance Monitor, Machine Learning Operations, Hardware Infrastructure, Model Inference
- **Published:** October 9, 2026
- **Apply:** https://www.careerjet.de/jobad/de62a8736c77e291b07169843c9cc0e2f8

## About the Role

* 3+ years of experience in DevOps, SRE, or backend infrastructure roles
 * Strong Python skills
 * Solid Linux and Bash expertise
 * Experience operating production cloud infrastructure
 * Bonus: experience with GPU infrastructure or LLM model serving
 * Ability to work onsite in Munich, Germany
 * Valid EU work authorization

## Description

As Senior DevOps Engineer, you will design and operate the cloud infrastructure that powers our in-game AI. Your main focus is the inference layer behind our LLM-driven gameplay, which means GPU hosting, model serving, and the surrounding backend needed to run language models reliably at scale.
Responsibilities

 * Design, build, and operate the cloud infrastructure for LLM inference and AI workloads
 * Set up and manage GPU-based hosting and model serving environments
 * Build reliable, scalable backend services that connect the game to our AI systems
 * Monitor performance, latency, and cost, and continuously optimize the stack
 * Automate deployments, scaling, and recovery wherever possible
 * Work closely with engineering to ensure infrastructure meets gameplay and product requirements
 * Evaluate and select the right cloud providers and tools as the stack evolves
 * Maintain strong security, reliability, and operational standards across all services