Platform Engineer: Build Scalable ML Infra

Q Innovations; Stockholms kommun; On-site; SEK 700,000 - 1,100,000; Full time

Job summary

Q Innovations in Stockholm is seeking a Platform Engineer to design and operate cloud infrastructure for large-scale consumer platforms, focusing on compute, networking, GPU management, and cost efficiency.

You will build Kubernetes-based orchestration systems, ML model serving infrastructure with canary/shadow deployments, and low-latency inference within production constraints. Apply CI/CD, data governance, and full observability to ensure reliability.

Qualifications

• Master's degree in Computer Science, Software Engineering, or equivalent; or proven production experience.
• 2+ years of experience operating production infrastructure at meaningful scale.
• Kubernetes expertise at scheduler/runtime level, not just config.
• Experience operating ML workloads in production (model versioning, inference scaling, GPU management).
• Infra-as-code practices applied across the stack.

Responsibilities

• Design and operate cloud infrastructure for large-scale platforms, focusing on compute, networking, GPU management, and cost efficiency.
• Build Kubernetes-based orchestration systems with robust scheduling, isolation, and reliability.
• Develop ML model serving infrastructure with multi-version support and low-latency inference.
• Create CI/CD pipelines to enable fast, confident deployments.
• Design data architectures with access controls and audit logging from day one.
• Build observability tooling for distributed tracing, monitoring, and alerting in production.

Skills

Kubernetes expertise

ML inference in production

Infrastructure-as-code

Production-scale systems design

Cloud infrastructure

Education

MSc in Computer Science or related field

Job description

Q Innovations in Stockholm is seeking a Platform Engineer to design and operate cloud infrastructure for large-scale consumer platforms, focusing on compute, networking, GPU management, and cost efficiency.

You will build Kubernetes-based orchestration systems, ML model serving infrastructure with canary/shadow deployments, and low-latency inference within production constraints. Apply CI/CD, data governance, and full observability to ensure reliability.