Senior DevOps / Platform Engineer, AI Infrastructure (m/f/x)

You will develop an existing platform and shape its next stage across architecture, automation, observability, security, and AI infrastructure. Our environment combines self-administered Linux servers, European infrastructure providers, dedicated hardware, and services from AWS, Azure, and GCP. Over time, we will also expand our European infrastructure and inference options as one part of our platform strategy.

This is a hands-on senior individual contributor role without people management. You will initially be the only dedicated Platform Engineer, working closely with our software engineers and company leadership.

We are opening this role to remote candidates across Germany. For this setup to work, you need a strong track record of independently operating production systems, communicating proactively, and moving complex infrastructure work forward without constant coordination.

Tasks

• You take technical ownership of MAIA’s production infrastructure. You operate and evolve self-administered Linux systems across virtual machines and dedicated servers, including containers, networks, reverse proxies, and API gateways.
• You make deployments safe, repeatable, and easy for engineers to use. You improve our Infrastructure as Code, GitHub Actions workflows, deployment processes, automated checks, versioning, and rollback capabilities.
• You operate and improve PostgreSQL in production. This includes performance analysis, connection pooling, capacity planning, backups, and regularly tested restore procedures.
• You develop our self-hosted observability stack. You connect metrics, logs, traces, and actionable alerts so that we understand system behaviour and identify problems before they affect more customers.
• You strengthen security across our infrastructure. You implement and maintain IAM, least privilege, secrets management, TLS, vulnerability scanning, and patch management.
• You implement technical controls for ISO 27001. You design them so that evidence is generated continuously and remains understandable and auditable.
• You help shape our AI infrastructure. You integrate model and inference providers and evaluate them based on reliability, latency, throughput, cost, and operational effort
• You improve incident response and operational resilience. You investigate root causes, establish useful runbooks, document operational knowledge, and turn incidents into lasting improvements.
• You improve the internal developer experience. You reduce manual work, create clear interfaces and workflows, and help engineers ship changes with confidence.
• You make infrastructure and inference costs transparent. You identify relevant cost drivers and help us make informed build, buy, and hosting decisions.

You will help determine the initial priorities after assessing the existing platform. We expect you to identify the most relevant risks, explain the available options, and take improvements through to reliable production operation.

Requirements

Your technical experience

• You have several years of experience operating production SaaS systems on Linux servers you or your team administered directly . Experience limited to fully managed hyperscaler services is not sufficient for this role.
• You have operated Docker and Docker Compose in production and understand reverse proxies or API gateways such as Traefik or Kong.
• You have practical experience operating PostgreSQL , including backups and restores you have personally configured and tested, performance analysis, and connection pooling.
• You have built and maintained CI/CD pipelines using GitHub Actions, GitLab CI, or comparable systems.
• You have managed infrastructure through Terraform, or comparable Infrastructure as Code tooling .
• You have operated an observability stack using tools such as Grafana, Loki, Prometheus, Sentry, or comparable technologies .
• You understand the security foundations of production infrastructure, including IAM, least privilege, secrets management, vulnerability scanning, and patching.
• You can design infrastructure that is reliable for customers and straightforward for engineers to use.
• You communicate fluently in English. German is helpful but not required.

Your AI foundation

You understand how RAG systems work and where they commonly fail in production. You can discuss the basic trade-offs involved in LLM serving, including latency, throughput, reliability, cost, and operational complexity.

You follow developments in models, inference providers, and the wider GenAI market closely enough to evaluate new options critically.

How you work

• You take responsibility from initial investigation through production operation.
• You investigate unfamiliar systems until you understand the relevant behaviour and failure modes.
• You make architecture decisions deliberately and document the reasoning behind them.
• You value maintainability, automation, tested recovery, and clear operational processes.
• You prioritise according to risk and impact and communicate trade-offs openly.
• You remain structured during incidents and communicate clearly with technical and non-technical stakeholders.
• You use AI tools productively while remaining accountable for every architecture decision and production change.
• You communicate proactively in a distributed team and make your progress, decisions, risks, and blockers visible.

The bar for this remote role

This position combines broad technical responsibility with a high degree of autonomy. For the remote setup, we are therefore looking for candidates who have already demonstrated that they can:

• independently operate business-critical production systems;
• identify and prioritise infrastructure work without waiting for detailed instructions;
• lead technical improvements across team boundaries;
• communicate reliably in writing and remotely; and
• remain accountable after a change has been deployed.

Interest in growing into these responsibilities is valuable, but for this particular opening, we need evidence that you have already carried a substantial part of them in practice.

Helpful, but not required

• Experience with Hetzner, NixOS, or self-hosted Supabase.
• Experience implementing technical ISO 27001 controls and audit evidence.
• Experience with SRE practices such as SLOs, error budgets, and incident reviews.
• Experience operating GPUs or serving LLMs with technologies such as vLLM.

Benefits

• 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.
• The opportunity to deepen your expertise in AI infrastructure and the operation of LLM workloads.
• Close collaboration with our engineering team, CTO, and company leadership.
• Short decision paths and the authority to move important infrastructure work forward.
• €75,000–€85,000 gross annual salary , depending on experience and scope.
• The opportunity to participate in our VSOP .
• A permanent, full-time position with 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.
• Access to a WellPass fitness membership.

This role is open exclusively to candidates currently based in Germany . Applications from outside Germany cannot be considered for this position.

Our hiring process consists of three stages:

• A 30-minute introductory conversation.
• A 90-minute technical interview.
• A final conversation with company leadership.

We move quickly and keep you informed throughout the process.

Instead of a traditional cover letter, please send us your CV and brief answers to these three questions:

• What is the most critical production system you have personally operated, and what were you directly responsible for?
• Tell us about one infrastructure risk, incident, or reliability problem you identified and improved.
• Why does this remote role and its level of ownership fit the way you work?

Please write these answers yourself and do not submit an AI-generated cover letter. We are not assessing polished marketing language. We want to understand your actual experience, judgement, and motivation.

We review this remote opening against a deliberately focused profile. If your experience matches the core requirements and you are ready to take independent responsibility for a growing AI platform, we would like to hear from you.

Find Jobs in Germany on Arbeitnow

Wir zeigen einen Auszug und einen Link je Anzeige, und den vollen Text, wenn die Quelle es erlaubt. Genannte Marken und Logos gehören ihren Inhabern.

Quelle: Statistisches Bundesamt (Destatis), Tabelle; dl-de/by-2-0; eigene Berechnung