Zum Inhalt springen
Neuer Job?Nejo!

Dein persönlicher KI-Karriere-Agent

MAmaia

Senior DevOps / Platform Engineer, AI Infrastructure (m/w/x) Berlin, Leipzig

ab 75.000 - 85.000 / Jahr
VollzeitRemoteSenior
AI/ML
Nejo KI-Zusammenfassung

Operating and evolving self-administered Linux systems for enterprise AI infrastructure. Several years of production SaaS systems operation on Linux servers required. VSOP participation, team travel covered.

Deine Match-Analyse

von deinem Karriere-Agenten

Warum dieser Job zu dir passt

Mögliche Lücken

Tipps für deine Bewerbung

Anforderungen

  • Several years of production SaaS systems operation on Linux servers
  • Production operation of Docker and Docker Compose
  • Understanding of reverse proxies or API gateways (Traefik, Kong)
  • Practical PostgreSQL operation experience
  • Built and maintained CI/CD pipelines
  • Managed infrastructure via Terraform or comparable IaC tooling
  • Operated observability stack (Grafana, Loki, Prometheus, Sentry)
  • Understanding of production infrastructure security foundations
  • Design reliable and user-friendly infrastructure
  • Fluent English communication
  • Understanding of RAG systems and common production failures
  • Discuss LLM serving trade-offs (latency, throughput, reliability, cost, complexity)
  • Follows GenAI market developments critically
  • Takes responsibility from investigation to production operation
  • Investigates unfamiliar systems to understand behavior and failure modes
  • Makes deliberate architecture decisions and documents reasoning
  • Values maintainability, automation, tested recovery, clear processes
  • Prioritizes according to risk and impact, communicates trade-offs
  • Remains structured during incidents, communicates clearly
  • Uses AI tools productively, remains accountable for changes
  • Proactive communication in distributed team, visible progress and blockers
  • Independently operate business-critical production systems
  • Identify and prioritize infrastructure work without instructions
  • Lead technical improvements across team boundaries
  • Reliable written and remote communication
  • Remain accountable after deployment
  • Evidence of substantial practical experience in core responsibilities
  • Experience with Hetzner, NixOS, or self-hosted Supabase
  • Experience implementing technical ISO 27001 controls and audit evidence
  • Experience with SRE practices (SLOs, error budgets, incident reviews)
  • Experience operating GPUs or serving LLMs (vLLM)

Aufgaben

  • Take technical ownership of MAIA’s production infrastructure
  • Operate and evolve self-administered Linux systems
  • Manage containers, networks, reverse proxies, and API gateways
  • Make deployments safe, repeatable, and easy to use
  • Improve Infrastructure as Code
  • Enhance GitHub Actions workflows
  • Streamline deployment processes
  • Develop automated checks
  • Manage versioning and rollback capabilities
  • Operate and improve PostgreSQL in production
  • Perform PostgreSQL performance analysis
  • Manage PostgreSQL connection pooling
  • Conduct PostgreSQL capacity planning
  • Oversee PostgreSQL backups and restore procedures
  • Develop our self-hosted observability stack
  • Connect metrics, logs, and traces
  • Implement actionable alerts
  • Strengthen security across our infrastructure
  • Implement and maintain IAM
  • Enforce least privilege principles
  • Manage secrets
  • Configure TLS
  • Conduct vulnerability scanning
  • Manage patch deployment
  • Implement technical controls for ISO 27001
  • Design systems for continuous evidence generation
  • Shape our AI infrastructure
  • Integrate model and inference providers
  • Evaluate providers based on reliability, latency, throughput, cost, and operational effort
  • Improve incident response and operational resilience
  • Investigate root causes of incidents
  • Establish useful runbooks
  • Document operational knowledge
  • Turn incidents into lasting improvements
  • Improve the internal developer experience
  • Reduce manual work for engineers
  • Create clear interfaces and workflows for engineers
  • Help engineers ship changes with confidence
  • Make infrastructure and inference costs transparent
  • Identify relevant cost drivers
  • Inform build, buy, and hosting decisions
  • Determine initial priorities after assessing the existing platform
  • Identify the most relevant risks
  • Explain available options for improvements
  • Take improvements through to reliable production operation

Berufserfahrung

ca. 4 - 6 Jahre

Ausbildung

Abgeschlossene BerufsausbildungODER
Bachelor-AbschlussODER
Master-Abschluss

Sprachen

Englisch – fließend
Deutsch – Grundkenntnisse

Tools & Technologien

LinuxSaaSDockerDocker ComposeTraefikKongPostgreSQLGitHub ActionsGitLab CITerraformGrafanaLokiPrometheusSentryIAMvLLMHetznerNixOSSupabase

Benefits

Attraktive Vergütung
  • VSOP participation
Team Events & Ausflüge
  • Team meetings with travel and accommodation covered
Gesundheits- & Fitnessangebote
  • WellPass fitness membership

Von Nejo automatisch aufbereitet

Nejo hat diesen Job automatisch von der Website des Unternehmens maia erfasst und die Informationen auf Nejo mit Hilfe von KI für dich aufbereitet. Trotz sorgfältiger Analyse können einzelne Informationen unvollständig oder ungenau sein. Bitte prüfe immer alle Angaben in der Originalanzeige! Inhalte und Urheberrechte der Originalanzeige liegen beim ausschreibenden Unternehmen.

Zur Originalanzeige bei maia

Über das Unternehmen

MA
ITBerlin

MAIA ist die KI-Plattform für Industrieunternehmen, die komplexe Dokumente, Unternehmenswissen und agentische Workflows verbindet, um verlässliche Antworten zu liefern und Aufgaben effizienter zu gestalten.

?Note
Wie gut ist dein Lebenslauf?

Nejo bewertet ihn, und bringt ihn danach gemeinsam mit dir in Bestform.

Du hast noch keinen Lebenslauf?

Noch nicht perfekt?

  • LiveEO GmbH
    Senior DevOps / Platform Engineer - Secure Infrastructure (m/w/x)
    Vollzeitmit HomeofficeSenior
    Berlin
  • Eye Security
    Senior Infrastructure Engineer – AI Platform (m/w/x)
    Vollzeitmit HomeofficeSenior
    Berlin
  • Market Logic Software AG
    Senior DevOps Engineer (m/w/x)
    Vollzeitmit HomeofficeSenior
    Berlin
  • Mercanis
    Senior DevOps Engineer (m/w/x)
    Vollzeitmit HomeofficeSenior
    Berlin
    ab 60.000 - 65.000 / Jahr
  • Workist GmbH
    Senior Platform Engineer (m/w/x)
    Vollzeitmit HomeofficeSenior
    Berlin
    ab 80.000 - 100.000 / Jahr