At deepset, we’re on a mission to make custom AI solutions accessible to every organization. With Haystack, thousands of developers build advanced LLM applications every day, while our enterprise-ready AI Platform helps companies turn large language models into business value. We’re remote-first, flexible, and built on a culture of trust and ownership. You’ll collaborate with top-tier tech talent, tackle meaningful challenges, and help transform complex AI into solutions that are simple, powerful, and ready for the real world.

Design & Land 

• Own technical outcomes from POC → production: integrations, data connectors, workflows, and infra-as-code (Kubernetes/Terraform/Helm).

• Produce reference architectures and reusable templates; upstream patterns to Product to reduce future “custom” work.

• Unblock enterprise environments: identity (OIDC/SAML), networking, storage, GPU scheduling, observability hooks.
  
  

Run & Harden 

• Define SLOs/Error Budgets with customers; implement end-to-end observability (logs/metrics/traces) and dashboards.

• Create runbooks/playbooks; lead L3 incident response and RCAs; drive reliability roadmaps to closure.

• Plan/execute upgrades and security patches in change windows; ensure rollback and post-upgrade verification.

• Be an active member of the on-call rotation to make sure we deliver excellent customer experience 
  
  

Partner & Enable

• Train customer teams on operations and emergency procedures; hand off cleanly to Support/CSM.

• Prioritize reliability and “productization” backlog with Product/Engineering based on field signal.

• Document clearly: setup guides, diagrams, SLOs, testing/DR procedures, and “golden path” standards.
  
  

• Hands on experience in programming language in Python (needed for improvements, bug fixing and small feature builds)

• 5+ years across SRE/Platform/Solutions/FDE, with evidence of shipping customer-facing builds and operating production systems.

• Strong with Kubernetes, containers, Linux, IaC (Terraform/Helm), CI/CD, networking (TLS, DNS, ingress/LB), backup/restore.

• Observability stacks (Prometheus/Grafana/OpenTelemetry/ELK); scripting (Python/Bash).

• Enterprise integration experience (SSO, secrets, compliance); confident communicator with execs and engineers under time pressure.

• Must be resident of the European Union

• German language skills

• Remote-first setup with flexible hours & tech of your choice
• 30 days vacation + extra days for family sick leave
• Competitive salary & stock options for every team member
• Monthly sports & mental health support allowance with Oliva
• Annual learning & development budget
• Monthly team socials & in-person meetups
• Dog-friendly Berlin HQ