Senior DevOps / Platform Engineer, AI Infrastructure (m/w/d)

About This Opportunity

We are representing a well-funded AI platform company based in Leipzig, Germany. Our client is scaling their enterprise knowledge management solution and needs a Senior DevOps / Platform Engineer to take technical ownership of their infrastructure and operations.

This is a hands-on senior role without management responsibilities. You'll be the first dedicated platform engineer, working closely with the engineering team and leadership to evolve infrastructure architecture, automation, and operational standards. If you've been co-responsible for infrastructure in a small team and want to shape your own domain, this is an excellent next step.

Responsibilities

• Develop and operate self-administered Linux systems on European VMs and dedicated servers, integrating services from AWS, Azure, and GCP
• Manage Docker Compose deployments, networks, reverse proxies, and API gateways in production
• Evolve Infrastructure as Code, CI/CD pipelines, and deployment workflows to ensure safe, reproducible changes
• Take ownership of PostgreSQL in production: performance analysis, connection pooling optimization, capacity planning, and tested backup/restore procedures
• Develop the self-hosted observability stack, connecting metrics, logs, and traces with actionable alerting
• Implement security best practices including least privilege, secrets management, vulnerability scanning, and patch management
• Support ongoing ISO 27001 certification by implementing technical controls and automating compliance evidence
• Evaluate AI inference providers and operational models based on latency, throughput, cost, and reliability
• Explore and potentially implement LLM serving on GPU infrastructure, with focus on European sovereign hosting options
• Automate recurring tasks, document operational procedures, and systematically investigate incidents to drive continuous improvement

What We're Looking For

Required Technical Foundation:

• Several years operating production SaaS systems on self-administered Linux servers (experience solely with fully managed cloud services is insufficient)
• Proficiency with Docker and Docker Compose in production environments
• Hands-on experience with reverse proxies or API gateways such as Traefik or Kong
• Practical PostgreSQL operational experience including self-configured and tested backups/restores, performance analysis, and connection pooling
• Infrastructure management with Terraform or comparable tools
• CI/CD pipeline development with GitHub Actions or similar systems
• Experience operating an observability stack (e.g., Grafana, Loki, Prometheus)
• Solid understanding of production security fundamentals: permissions, secrets management, security updates
• Understanding of RAG system fundamentals and common operational failure modes
• Ability to evaluate trade-offs in LLM serving: latency, throughput, cost, and operational overhead
• Active interest in AI model and provider developments with ability to critically assess suitability for specific requirements
• Strong English communication skills (team language); German is a plus

How You Work:

• You combine independence with careful engineering, investigating unfamiliar systems until you understand relevant relationships
• You justify architecture decisions and test changes before production deployment
• You keep complexity manageable and value maintainability, documentation, and automation
• You prioritize based on risk and impact, seek input strategically, and communicate calmly during incidents
• You can explain technical concepts clearly to non-technical stakeholders
• You use AI tools productively and reflectively while maintaining personal responsibility for technical decisions

Helpful but Not Required:

• Experience with Hetzner, NixOS, or self-hosted Supabase
• Technical implementation and evidence gathering for ISO 27001
• SRE practices: SLOs, error budgets, incident reviews
• GPU operations and LLM serving (e.g., vLLM)

What's Offered

• Own technical domain with direct impact on architecture, operational quality, and engineering team productivity
• Opportunity to deepen AI infrastructure expertise and LLM workload operations
• Close collaboration with engineering and leadership with ability to shape long-term technical standards
• Permanent full-time position with flexible working hours
• Hybrid work model: minimum three office days per week in Leipzig, remote work other days
• Virtual share option plan (VSOP) participation
• WellPass membership access
• Relocation support to Leipzig (scope discussed individually)

How We Work With You

Our talent team at Get A Job.ai partners exclusively with this client to find the right platform engineering leader. When you apply through our platform, a specialized recruiter will screen your background and discuss the role in detail. We'll then submit qualified candidates directly to the client.

The client's interview process consists of a 30-minute initial conversation, a 90-minute technical interview, and a final discussion with leadership. They make decisions quickly and provide updates at every stage.

Please do not contact the client directly. All applications must come through Get A Job.ai to be considered.

To apply, please submit your CV along with a brief, personally written statement addressing: which production system you've been responsible for, what technical improvement you've driven, and why you want to shape this domain. The client values authentic, personally written applications over AI-generated cover letters.

Pay

The client offers €75,000 to €85,000 annual gross salary plus VSOP equity participation. This is paid directly by the employer upon hire.

Get A Job.ai is an equal opportunity recruiter. We welcome applications from all qualified candidates regardless of race, color, religion, sex, national origin, age, disability, or any other protected characteristic.