MLOps / AI Platform Engineer

Role overview Build the platform and operational practices that let AI systems move reliably from deployment to ongoing production releases. You’ll own MLOps and AI infrastructure across engagements, with a focus on observability, safe change management, and dependable performance under load.

Responsibilities - Create CI/CD workflows for deploying models, prompts, and AI services. - Monitor system drift, cost, latency, and quality, with useful alerts for operational issues. - Establish model and prompt versioning, rollback procedures, and safe deployment practices. - Manage inference infrastructure scaling and costs across cloud environments. - Build platform capabilities that help engineering teams deliver AI systems more efficiently.

Requirements - At least seven years in platform engineering, infrastructure, or MLOps. - Strong experience with Kubernetes, Docker, Terraform or Pulumi, and at least one major cloud provider. - Experience running ML or LLM systems in production, including their observability. - Python skills and the systems expertise to troubleshoot inference under load. - A reliability-focused approach and composure during incidents.

Nice to have - Experience with LLM observability tools and controlling token costs. - Background working in regulated or high-availability environments.

Benefits and work setup - Full-time, remote role for candidates in EMEA. - Listed compensation is $175,000–$220,000 plus equity.