Senior DevOps / MLOps Engineer (AI Agents, Claude)

Xebia is a global AI-first, digital transformation, and engineering partner. With over 25 years of experience and a team of 5,000 professionals across 16 countries, we help organizations design and build scalable products, platforms, and data-driven solutions.

We specialize in Artificial Intelligence, Data and Cloud, Intelligent Automation, and Digital Products, combining deep technical expertise with a strong focus on engineering excellence and a people-first culture.

In the CEE region, we’re a team of nearly 1,000 experts delivering modern applications, data platforms, and AI solutions for clients such as McLaren, Aviva, Deloitte, Spotify, Disney, ING, UPS, Tesco, Truecaller, AllSaints, Volotea, Schmitz Cargobull, Allegro, InPost, and many, many more. We work with leading technologies including AWS, Azure, GCP, Databricks, and Snowflake, and combine strong engineering culture with a consulting mindset and a continuous focus on growth and knowledge sharing.

We are looking for DevOps/MLOps Engineers to join a project delivered for our international client operating at the intersection of software engineering, artificial intelligence, and enterprise technology. The client is building and scaling AI-powered solutions based on autonomous AI agents, with multiple development teams working in parallel on separate AI agent applications and repositories.

This role is a great opportunity to work on the platform and operational foundations behind modern AI applications. You will be responsible for establishing reliable CI/CD, secure repository and access management, observability, and deployment processes for AI agents built within the .NET ecosystem.

The project combines DevOps, platform engineering, security, observability, and AI/MLOps within a distributed international environment. You will work closely with AI Engineers and software development teams using Claude and other LLM providers, helping establish the operational capabilities required to move AI agent solutions safely from development into production.

You will:

• design, implement, and maintain deployment processes for AI agents built on the .NET ecosystem,

• support multiple development teams working in parallel across separate AI agent repositories,

• establish and maintain GitHub Enterprise best practices, including branching strategies, Pull Request workflows, code reviews, and repository governance,

• implement and maintain CI/CD pipelines supporting reliable and repeatable AI agent delivery,

• manage secrets, credentials, tokens, and environment configurations following enterprise security best practices,

• implement secure access management based on the principle of least privilege,

• establish logging, monitoring, auditing, and operational visibility for AI agents and their integrations,

• implement observability solutions including dashboards, alerting, and distributed tracing where appropriate,

• support incident troubleshooting and operational readiness of AI-powered applications,

• collaborate closely with AI Engineers working with Claude and other LLM providers,

• support the future integration of Azure-hosted and self-hosted language models,

• contribute to secure and compliant development and deployment processes, including GDPR-related requirements,

• ensure test and development environments follow appropriate security and data handling practices,

• participate in technical reviews, architecture discussions, and operational readiness assessments,

• contribute to infrastructure automation, configuration management, and continuous improvement of the AI platform,

• support engineering teams in adopting reliable and scalable DevOps and MLOps practices,

Your profile:

• 5+ years of commercial experience in DevOps, Platform Engineering, SRE, Infrastructure Engineering, or similar roles,

• strong hands-on experience with GitHub Enterprise and Pull Request-based development workflows,

• proven experience designing and maintaining CI/CD pipelines,

• strong understanding of environment management, release processes, and deployment automation,

• practical experience with infrastructure automation and configuration management,

• strong Linux administration and cloud engineering background,

• experience working with enterprise-scale software development environments,

• strong understanding of secrets management, identity and access management, and least-privilege security models,

• experience implementing audit logging and secure software delivery practices,

• understanding of enterprise security, governance, and compliance requirements,

• hands-on experience with logging, monitoring, distributed tracing, operational dashboards, and incident troubleshooting,

• previous experience supporting AI, GenAI, LLM, or MLOps workloads,

• good understanding of LLM-based applications and AI agent architectures,

• familiarity with Anthropic Claude, OpenAI, Azure OpenAI, or similar LLM platforms,

• understanding of the deployment, monitoring, security, and operational challenges associated with AI-powered applications,

• experience supporting software engineering teams building and deploying AI applications,

• strong communication and collaboration skills,

• ability to work independently and take ownership in distributed international teams,

• practical experience using AI-powered assistants (e.g. Claude Code, GitHub Copilot, Cursor) to improve productivity, quality, or decision-making in software delivery.

• Work from the European Union region and a work permit are required.

Nice to have:

• hands-on experience with Microsoft Azure,

• experience working with Azure OpenAI,

• experience with AI observability, model monitoring, or LLM application monitoring,

• experience with Docker and other containerized deployment technologies,

• experience supporting .NET development teams,

• experience working on AI Agent, GenAI, RAG, or Agentic AI initiatives,

• familiarity with MLOps platforms, workflows, and model lifecycle management,

• experience working within enterprise governance, compliance, or regulated environments,

• experience implementing security and operational controls specifically for AI workloads,

• practical experience using AI-assisted development tools such as Claude Code, GitHub Copilot, Cursor, or similar technologies,

• experience designing scalable platform capabilities that support multiple AI engineering teams,

• experience applying GenAI in a more structured way within the SDLC, including defined workflows, prompt patterns, or tool integrations embedded into daily work.

• Interest in and familiarity with emerging AI-driven practices (e.g. agent-based workflows, automation patterns, AI-augmented development), with a willingness to explore and experiment beyond standard approaches.

Recruitment Process:

CV review – HR call – Interview – Client Interview – Decision