TL;DR Site Reliability Engineer to own and evolve deepset's cloud and customer infrastructure end to end. You'll work across SaaS, private cloud, and on-prem environments to make our self-hosted platform production-ready, drive CI/CD and GitOps maturity, and reduce complexity at scale. Your work will directly shape how deepset's AI platform is built, deployed, and scaled for our own cloud and for customers running it in their own environments.]]> Why deepset Haystack, thousands of developers build advanced AI applications, while our Enterprise platform helps teams scale across use cases, users, and environments. We’re remote-first, flexible, and built on trust and ownership. You’ll work alongside strong technical talent, take on meaningful challenges, and help turn complex AI into solutions that are practical, reliable, and ready for the real world.]]> What you will do

Build and operate real-world infrastructureDesign, configure, and evolve infrastructure that runs both in our cloud and inside customer environments (SaaS, private cloud, on-prem).
Make self-hosted production-readyHelp us deliver a production-grade, self-hosted platform that can be deployed on any Kubernetes setup in weeks - not months.
Drive automation & platform maturityImprove CI/CD pipelines, GitHub workflows, and GitOps setups so teams can ship faster with confidence.
Reduce complexity and costContinuously simplify systems and optimize infrastructure spend without compromising performance or reliability.
Shape how we buildChampion best practices in reliability, scalability, and security across the organization, not as rules, but as working systems.

]]> Requirements

2-5 years of experience working with large-scale production infrastructure

Fluent German language skills

Experience with distributed or service-oriented architectures

Hands-on expertise with:

AWS
Kubernetes
CI/CD and GitOps (e.g. ArgoCD)

Working knowledge of Infrastructure as Code (Terraform preferred)

Solid troubleshooting skills - you can debug across systems, not just within one layer

A pragmatic mindset: you balance speed, simplicity, and reliability

Ownership and accountability - you take responsibility for systems end-to-end

Ability to work independently while staying aligned with the team’s goals

]]> Nice to have

Familiarity with observability stacks (e.g. Datadog, Prometheus)

Experience optimizing cloud costs at scale

Interest or experience in Machine Learning / LLM systems

Experience improving developer experience and platform tooling using AI agents

Contributions to SRE practices like postmortems, SLIs/SLOs, and reliability engineering culture

]]> Benefits

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

]]>