Senior DevOps / MLOps Engineer

Engineering Glasgow / Remote Consultant Contract

As a Senior DevOps/MLOps Engineer at Kodamai, you will own the end-to-end infrastructure strategy, from setting up and maintaining our GCP-based internal environments to advising clients on optimal deployment architectures. You will design, implement, and continuously improve the pipelines and platforms that underpin both Kodamai's core technology and the solutions we build for clients.

Key Responsibilities

• GCP Infrastructure & Internal Dev Environments
• Design, provision, and manage GCP infrastructure (GKE, Cloud Run, Compute Engine, Cloud Storage, VPC, IAM) for Kodamai's core technology platform.
• Build and maintain internal development environments for client project teams, ensuring reliability, security, and cost efficiency.
• Define infrastructure-as-code (IaC) standards across all environments.
• Implement robust monitoring, alerting, and logging using GCP-native tools (Cloud Monitoring, Cloud Logging) and third-party stacks (Prometheus, Grafana).
• Client Deployment Advisory & Requirements Analysis
• Engage with clients to analyze their existing deployment infrastructure and constraints.
• Provide tailored recommendations on deployment strategies, tooling, and architecture patterns that integrate seamlessly with their current environment.
• Produce technical assessments and deployment architecture proposals as part of pre-sales and onboarding processes.
• Act as a trusted technical advisor to client engineering teams during implementation and go-live phases.
• Design and implement end-to-end CI/CD pipelines.
• Establish branching strategies, release management processes, and deployment gating (automated testing, security scans, approvals).
• Ensure high pipeline reliability, fast feedback loops, and clear rollback mechanisms.
• Champion DevOps best practices across engineering teams - documentation, runbooks, and post-mortems.
• MLOps
• Support the operationalization of ML models - model versioning, experiment tracking, and deployment workflows.
• Work with data science teams to configure MLOps tooling such as Vertex AI, MLflow, Kubeflow, or similar platforms.
• Enable automated model retraining, drift detection, and performance monitoring pipelines.