Senior AI Platform Engineer

At Avaron, you get the security of permanent employment combined with the variety of working at different customers. We place specialists across everything from tech, IT and industry to project management and business support – and whatever the assignment, you have a consultant manager who is there for you and your development.

You will help build and operate a shared AI platform that enables responsible, scalable use of LLM services across a larger organisation. The work spans the core building blocks needed for secure adoption: gateway capabilities, governance, access control, cost visibility, developer templates and operational support.

This is not a greenfield experiment. You are expected to bring hands-on experience from a similar platform build and use that knowledge to improve design choices, controls and developer experience from day one. It is an interesting role if you enjoy combining platform engineering, AI enablement and governance in a setting where your work becomes the foundation others build on.

• You will build and operate an AI gateway on Azure using services such as Azure OpenAI or AI Foundry, Entra ID and APIM.
• You will establish a governed repository of approved agents, including ownership, permissions and defined data scope.
• You will create a cost telemetry pipeline so every request can be traced to a cost centre and a concrete use case.
• You will automate access provisioning and licence lifecycle management for AI tools adopted across the organisation.
• You will produce developer golden paths, including templates for RAG, agents and evaluation.
• You will establish observability, logging and runbooks so routine platform operations can be handled efficiently.
• You will contribute to policy enforcement, model routing and secure access patterns that support reliable enterprise use of AI services.

• You have built an AI governance platform end to end before and can clearly explain what you built, what it governed, who used it and what you would change in a second implementation.
• You have production experience running containerised workloads on Kubernetes that other teams depended on.
• You have worked with AI gateway or LLM proxy engineering using APIM, Kong, LiteLLM or equivalent technology.
• You have practical experience with LLM applications, including API integration, token cost behaviour, evaluation and RAG patterns.
• You have owned observability in production using OpenTelemetry, Grafana, Log Analytics or equivalent tools.
• You have strong backend engineering skills in Python or TypeScript, together with Infrastructure as Code and CI/CD using tools such as Terraform, GitHub Actions or Azure Pipelines.
• You have experience with identity and access engineering, including SSO, RBAC and service principals.
• You have built an internal platform or developer service that other teams chose to adopt.
• You communicate fluently in Swedish and English.

• Backend engineering experience in Go.

• Permanent employment at Avaron AB
• Occupational pension
• Wellness allowance of SEK 5,000 per year

Selections are made on an ongoing basis – apply as soon as you can.