About the role

We're hiring an MLOps / Platform Engineer to build the infrastructure that lets our teams ship AI safely and repeatedly. You'll own deployment, monitoring, and CI/CD for LLM and ML systems across cloud environments — turning one-off launches into a paved road every engineer can follow.

What you'll do

• Build and operate CI/CD pipelines for model and service deployment across cloud platforms.
• Stand up monitoring and observability for production LLM systems — latency, cost, drift, and quality.
• Manage infrastructure as code and the tooling that supports AI workloads at scale.
• Harden systems for security and compliance in regulated environments.
• Partner with engineers to reduce time from prototype to production.

What you'll bring

• 4+ years in DevOps, platform, or MLOps engineering.
• Strong experience with at least one major cloud (Azure, AWS, or GCP) and infrastructure as code (Terraform).
• Comfort with containers and orchestration (Docker, Kubernetes) and CI/CD tooling.
• A reliability-first mindset and good judgment around cost and security.

Nice to have

• Experience deploying ML on Azure ML, AWS Bedrock, or GCP Vertex AI.
• Familiarity with model observability tools (LangSmith, Arize, or similar).
• Exposure to compliance frameworks (SOC 2, HIPAA).