Senior DevOps – Platform Engineer, AI Infrastructure

• Take technical ownership of MAIA’s production infrastructure
• Operate and evolve self-administered Linux systems across virtual machines and dedicated servers
• Manage containers, networks, reverse proxies, and API gateways
• Improve Infrastructure as Code, GitHub Actions workflows, deployment processes, automated checks, versioning, and rollback capabilities
• Operate and improve PostgreSQL in production, including performance analysis, connection pooling, capacity planning, backups, and tested restores
• Develop the self-hosted observability stack across metrics, logs, traces, and actionable alerts
• Strengthen infrastructure security through IAM, least privilege, secrets management, TLS, vulnerability scanning, and patch management
• Implement technical controls for ISO 27001 with continuously generated, understandable, and auditable evidence
• Shape AI infrastructure by integrating and evaluating model and inference providers
• Explore self-hosted LLM inference, potentially including GPU infrastructure and vLLM
• Improve incident response and operational resilience through root-cause investigations, runbooks, documentation, and lasting improvements
• Improve internal developer experience by reducing manual work and creating clear interfaces and workflows
• Make infrastructure and inference costs transparent and support build, buy, and hosting decisions
• Assess the existing platform, identify risks, explain options, and take improvements through reliable production operation
• Work closely with software engineers, the CTO, company leadership, and distributed teammates
• Serve as the first and initially only dedicated Platform Engineer without people management

• Several years of experience operating production SaaS systems on Linux servers administered directly by you or your team
• Experience with Docker and Docker Compose in production
• Understanding of reverse proxies or API gateways such as Traefik or Kong
• Practical PostgreSQL operations experience, including personally configured and tested backups and restores, performance analysis, and connection pooling
• Experience building and maintaining CI/CD pipelines using GitHub Actions, GitLab CI, or comparable systems
• Experience managing infrastructure through Terraform, Pulumi, or comparable Infrastructure as Code tooling
• Experience operating observability stacks using Grafana, Loki, Prometheus, Sentry, or comparable technologies
• Understanding of IAM, least privilege, secrets management, vulnerability scanning, and patching
• Ability to design reliable infrastructure that is straightforward for engineers to use
• Fluent English
• German helpful but not required
• Understanding of RAG systems and common production failure modes
• Ability to discuss LLM-serving trade-offs involving latency, throughput, reliability, cost, and operational complexity
• Close tracking and critical evaluation of models, inference providers, and the GenAI market
• Ability to independently operate business-critical production systems
• Ability to identify and prioritize infrastructure work without detailed instructions
• Ability to lead technical improvements across team boundaries
• Reliable written and remote communication
• Accountability after changes are deployed
• Helpful but not required: experience with Hetzner, NixOS, self-hosted Supabase, ISO 27001 controls and audit evidence, SRE practices, GPU operations, or LLM serving with vLLM

• A substantial technical area to shape and own in a well-funded, growing AI startup
• Direct influence on MAIA’s architecture, reliability, security, and engineering productivity
• Opportunity to deepen expertise in AI infrastructure and LLM workload operations
• Close collaboration with the engineering team, CTO, and company leadership
• Short decision paths and authority to move important infrastructure work forward
• Opportunity to participate in the VSOP
• Permanent, full-time position
• Flexible working hours
• Fully remote work from anywhere within Germany
• Regular opportunities to meet and work with the team in Leipzig, with travel and accommodation covered
• WellPass fitness membership
• €75,000–€85,000 gross annual salary, depending on experience and scope