Platform Engineer

Role: AI Platform Engineer

Location: Stockholm, Sweden

Assignment Description

We are currently looking for AI Platform Engineers.Platform developer for an on-premises AI platform based on NVIDIA AI Enterprise with Kubernetes and Run:AI. Responsible for launching applications and support functionality within the platform so that development teams and analysts can easily utilize GPU resources.

The consultant will be part of an AI platform team where employees and consultants work together. In the broader context, we collaborate with established development teams responsible for the DevOps and data platform, as well as with data teams within the business. The AI platform is in a startup phase, so there are good opportunities for an experienced consultant to help shape the solution. However, this assignment is primarily about developing source code.

Requirements

Must have:

• Experience in development, deployment, and operation of containerized applications (e.g., Docker, Podman, Compose, Kubernetes).
• Knowledge of modern AI models and tools (e.g., LLM, RAG, MCP).
• Experience in developing, launching, and operating applications in Kubernetes (e.g., ArgoCD, OpenShift, Kustomize).

Nice to have:

• Experience in application logging and monitoring (e.g., Prometheus, Grafana).
• Experience in deploying GPU-based applications (e.g., LLM inference, PyTorch, TensorFlow, JAX).
• Knowledge of the NVIDIA AI Enterprise stack (e.g., Run:AI, NeMo, NIM, Triton).
• Experience in developing in the Python programming language within data and/or AI (e.g., Polars, Pydantic AI, FastAPI).(
• Experience in developing, launching, and operating modern AI models and tools (e.g., LLM inference, RAG, MCP).

Individual qualities:

• Good ability to share experiences and train colleagues.
• Understanding of security requirements and the ability to work productively in a public authority context.
• Ability to work in an agile development team.
• Self-reliant/Independent.
• Solution-oriented.