Senior DevOps/MLOps Engineer (AI)

TL;DR

Senior DevOps/MLOps Engineer (AI): Building and scaling infrastructure for Edge AI and Computer Vision systems with an accent on multi-cloud architecture, Kubernetes orchestration, and MLOps pipelines. Focus on architecting secure, reliable networking across cloud and edge environments and driving platform engineering standards for high-scale global deployments.

Location: Must be based in or able to work from Berlin, Germany (hybrid: 3 days in-office)

Company

hirify.global is a fast-growing technology company developing edge-based computer vision solutions for international retail markets.

What you will do

• Take end-to-end ownership of multi-cloud infrastructure (AWS, GCP, Azure) from design to operation.
• Build and evolve a scalable platform engineering layer to support all engineering teams.
• Architect complex hybrid networking, routing, and secure communications for cloud and edge deployments.
• Design MLOps workflows including data pipelines, GPU orchestration, and model deployment.
• Drive security compliance standards and implement deep system observability.
• Collaborate with leadership on infrastructure strategy and long-term technical architecture.

Requirements

• 5+ years of experience in DevOps, platform, or infrastructure engineering.
• Proven ability to design and operate complex production cloud architectures.
• Strong Kubernetes expertise and proficiency in Infrastructure-as-Code (Terraform).
• Deep understanding of networking fundamentals, cloud networking, and security layers.
• Proficiency in Python and/or Go for building robust systems.
• Strong Linux and distributed systems knowledge.

Nice to have

• Experience with configuration management tools like Ansible.
• Familiarity with distributed data systems and on-prem/edge infrastructure.
• Experience leading incident response and defining SLOs.

Culture & Benefits

• High-impact environment influencing production systems at scale.
• Steep growth curve working with multi-cloud, edge computing, and AI infrastructure.
• Collaboration with a team of highly experienced engineers.
• Defined career path into Staff Engineering or technical leadership roles.
• Hybrid work policy allowing for flexibility.