About cortecs.ai
At cortecs.ai, we build AI infrastructure that helps European companies use AI models reliably, cost-effectively, and with strong data protection.
Our platform gives customers one unified API to access leading AI models across providers, with intelligent routing, observability, spend controls, and privacy-by-design infrastructure. We help companies regain control over their AI spend and strengthen European data sovereignty.
We are building for teams that care about quality, reliability, latency, and cost in production AI systems. Our users are technical, demanding, and close to us, which means the feedback loop is short and the work is grounded in real problems.
About the role
We are looking for software engineers who want to build the core infrastructure behind cortecs.ai.
You will work on model routing, provider orchestration, backend APIs, cloud infrastructure, reliability, spend controls, and observability. This is a role for someone who enjoys backend engineering, distributed systems, and building the infrastructure that makes AI systems reliable in production.
What you'll work on
- Architect, build, and operate the cloud infrastructure behind cortecs.ai, including deployment pipelines, monitoring, scaling, and production reliability.
- Design, develop, and maintain secure, scalable backend services and APIs for routing requests across AI models and providers.
- Build provider orchestration systems that handle latency, reliability, cost, fallbacks, rate limits, and failure cases in production.
- Automate deployments, improve CI/CD workflows, monitor system performance, and troubleshoot infrastructure issues across the stack.
- Build observability and spend-control tools so teams can understand, debug, and optimize their AI usage.
- Collaborate with engineering, legal, and compliance experts to ensure our architecture supports strong European data privacy standards.
- Help define the infrastructure strategy that allows cortecs.ai to scale reliably as the product and customer base grow.
- Shape core product and architecture decisions in a small engineering team.
How we work
- We stay close to users: our active developer and customer community gives us a direct pulse on how cortecs.ai is used in practice and what needs to improve next.
- We keep feedback loops short and involve engineers directly in product decisions.
- We value calm, focused execution and protect time for deep technical work.
- We work async where it makes sense, with clear written communication.
- We care about robust systems, clear thinking, and pragmatic tradeoffs.
You might be a fit if
- You have strong backend engineering experience and enjoy building production systems.
- You are comfortable with APIs, databases, queues, cloud infrastructure, containers, and CI/CD workflows.
- You have experience with Python, JavaScript/TypeScript, Rust or similar.
- You care about reliability, observability, performance, security, and clean system design.
- You like turning ambiguous product problems into simple, maintainable technical solutions.
- You communicate clearly in English and enjoy working close to users and product context.
- Experience with AI infrastructure, LLM APIs, model providers, Kubernetes, Infrastructure as Code, or GDPR/data privacy topics is a strong plus.
What we offer
- Flexibility: Uncapped home-office options and flexible working hours, so you can work where and when you are most productive.
- Our workspace: A desk in a brand-new, modern office in the heart of Vienna.
- Compensation: Competitive annual gross salary starting from €65,000, with strong willingness to overpay based on qualifications and seniority, plus equity options.
- Equipment: Modern hardware and the tools you need to do your best work.
Apply
If this sounds interesting, we would love to hear from you.
Please send Jakob Kilbertus a connection request on LinkedIn with a short note including:
- your CV, GitHub, or personal website
- 3-5 sentences about work you are proud of
- optionally, one thing you would be curious to improve or build at cortecs.ai
- We care more about thoughtful signal than polished applications, so a short, specific note is perfect.