Job
In this role, you will review AI components and prototypes from the engineering team, optimize them for production, and make architectural decisions to develop and operate secure, scalable AI systems.
This listing has been machine translated. Show original
Job technologies
Your role in the team
- Review AI components, prototypes and tooling proposals from the AI engineering team, harden them into production systems and act as the technical gatekeeper for every deployment.
- Make the architecture decisions: which model-serving stack to use, when to isolate workloads, when on-premises is better than the cloud, and where the right abstraction layer belongs.
- Own our multi-cloud and on-prem footprint across AWS, GCP, Azure and customer-hosted setups, and evolve our Kubernetes platform with ArgoCD, Terraform, GitHub Actions, Prometheus and Grafana.
- Invent the sandbox, runtime, and isolation patterns that let AI engineers move fast without compromising compliance, and extend our TypeScript microservices and APIs where needed to unblock the team.
- Embed threat modeling, secure SDLC, secrets management, and supply-chain security into our pipelines, and own ISO 27001 and EU AI Act controls on the platform side.
- Design on-premises deployment patterns for enterprise clients with the highest security requirements, and find creative solutions where off-the-shelf setups fall short.
- Build LLM-ready environments, from model serving (vLLM, TGI, Triton or similar), inference scaling and GPU orchestration to vector stores, RAG infrastructure and the observability hooks that show what our AI systems actually do in production.
Our expectations of you
Education
- 7+ years of experience in platform, infrastructure, SRE, or DevSecOps roles, with hands-on exposure to AI or ML systems in production, plus a degree in Computer Science, Software Engineering, Electrical Engineering, or a comparable field—or equivalent practical experience.
Qualifications
- Production-grade expertise with Kubernetes, ArgoCD, Terraform, GitHub Actions, Prometheus, and Grafana across at least two of AWS, GCP, Azure, and on-premises environments.
- Code literacy in TypeScript: You critically review backend code, push back where it matters, and contribute targeted changes.
- A creative problem solver: you enjoy tackling problems with no known solution, find unconventional ways to work around technical and regulatory constraints, and turn new ideas into patterns others can build on.
- Pragmatic and self-directed: you deliver effective solutions instead of collecting elegant designs, identify what needs to be done without being told, and explain trade-offs clearly, including in occasional technical conversations with enterprise clients.
- LLM systems understanding: you know how LLM architectures and inference pipelines work and where they fail in production. You don't train models from scratch, but you can judge what an AI system will actually do under real load.
- AI infrastructure fluency: you are comfortable with model serving, RAG, embeddings, vector databases, and evaluation tooling, and you have an informed opinion on what is worth adopting next.
- AI as a daily multiplier: You use AI tools to improve DevOps workflows, automate infrastructure tasks, and accelerate your own delivery. You try new tools early and feed what you learn back into the Blockbrain product.
Experience
- Practical DevSecOps experience with threat modeling, secure SDLC, secrets management, and supply chain security in environments shaped by ISO 27001, the EU AI Act, or comparable standards.
- Hands-on experience building secure, scalable environments for LLM workloads, including model serving, vector stores, RAG, observability and sandbox patterns.
What we offer
- Flexible Work Models: Work where and when you do your best work. You're on-site in Hamburg 2-3 days a week, with flexible working hours. After probation, you can also work from abroad for up to 8 weeks per year.
- Benefits That Make a Difference: Deutschland-Ticket, Wellpass fitness membership, access to the latest AI tools, and regular company and team off-sites that bring us together.
- Top team: Work with an international team of exceptional people who raise the bar every day and love building together.
- High Growth Potential: Don’t just shape processes—shape the company. You’ll learn quickly, take real ownership, and influence our future direction at a fast-growing AI startup.
- Top equipment: MacBook, iPhone, headset, and every tool you need to do your best work from day one.
- Very Competitive Package: We offer a highly competitive package overall: a strong fixed salary plus a variable component that rewards the impact you create.
Topics you will work on
Job locations
About your employer
Blockbrain focuses on automating document processes and enhancing knowledge management. The platform increases efficiency and optimizes the use of corporate knowledge.
- Startup
- Onsite, Hybrid
- Internet, IT, Telecommunication
More jobs
These jobs might also interest you
Hello, let's say WE! We - the HUK-COBURG Insurance Group - are among the top 10 in Germany. Founded over 90 years ago, we are now the leading insurer for private households with over 13 million customers and the largest German auto insurer. Our...
Anyone who joins here not only designs software – they bring machines to life that are recognizable on real construction sites. Software Developer (m/f/d) Basic Engineering Our client is an internationally leading manufacturer of technically...
Participation in security analyses and assessment of applications and IT systems. Support in the design and implementation of technical security measures (e.g., WAF, Load Balancing, Firewall, etc.). Conducting and supporting penetration tests,...