Lead Infrastructure & Platform Engineer (Cloud & ML Serving)

Would you build a platform that serves machine learning models in real time to hundreds of thousands of users?

We are looking for a Lead Infrastructure & Platform Engineer for a deep-tech, AI and imaging-focused project, who will take full ownership of the cloud and serving architecture.

About the role:

• Designing and operating cloud infrastructure (AWS / GCP / Azure)
• Bringing ML models into production and scaling them
• Developing high-load backend systems (API, inference, data)
• Not just operations: writing production server-side code is also part of the job
• Making platform-level decisions around performance, latency, and reliability

Requirements

What we are looking for

• 8+ years of experience in cloud, platform engineering, or distributed systems
• Strong background in AWS, Kubernetes, CI/CD, and Infrastructure as Code (IaC)
• Experience with ML serving, GPU inference, and real-time systems
• Confident programming skills in Python and C++ (not just scripting-level knowledge)
• Deep expertise in scaling, latency optimization, fault tolerance, and observability

Benefits

Why is this interesting?

• It’s not classic DevOps: it sits at the intersection of platform engineering, software development, and machine learning
• End-to-end ownership (from infrastructure → backend → ML serving)
• Building a high-scale system with real production traffic
• Startup environment with real technical decision-making autonomy

If you’re looking for a role where you don’t just operate systems, but actually build the foundations of the platform, we should talk.