LLMOps / AI Platform Engineer

WeQuelStockholm, StockholmHybridFull-timeMid level, 2–5 yearsListed 5 hours ago

Apply now

About this role

LLMOps / AI Platform EngineerWeQuel is looking for an LLMOps / AI Platform Engineer for an assignment with one of our clients. You will build and operate the shared platform that lets teams run agentic workflows in production – secure, observable and cost-efficient.About the assignmentWorkload: 100%Location: HybridLanguage: EnglishYour responsibilitiesOperate model gateways, MCP servers, vector databases and agent runtimesBuild CI/CD for prompts, agents and evaluations, including versioning and regression testingSet up observability: tracing, logging, cost per call, latency and error ratesHandle secrets, networking, rate limits and secure access to internal systemsAutomate infrastructure with Infrastructure as Code and provide templates ("golden paths") for development teamsRequirementsAt least 4 years of experience in DevOps, platform engineering or MLOpsStrong experience with Kubernetes, containers and Infrastructure as Code (Terraform or Bicep)Experience running LLM services in the cloud (e.g. Azure OpenAI, AWS Bedrock)Experience with observability stacks (e.g. OpenTelemetry, Grafana, Datadog)Fluent English, written and spokenMeritoriousLLM-specific observability tools (e.g. Langfuse, LangSmith, Arize)FinOps for AI and cloud costsPython developmentBackground in industrial or manufacturing environmentsSwedishWho you areYou are a reliable, automation-minded engineer who likes to make other teams faster. You think in terms of stability, security and cost, and you communicate clearly about trade-offs.Applications are reviewed continuously – apply today!