Your responsibilities:

• Working on Python programs – new development and enhancements.
• Build transformer / Agent architecture on cloud platform (GCP)
• Packaging and serving models using containers and KServe/Vertex endpoints, as well as
• Working with feature and model registries, model monitoring and drift detection
• GPU Scheduling
• Canary and Shadow deployments.
• Collaborate with cross-functional teams to understand requirements and translate them into platform solutions.
• Troubleshoot platform and deployment issues, perform root-cause analysis and implement permanent fixes

Your Profile

Essential skills/knowledge/experience:

• 6+ yrs Experience
• Kubernetes/OpenShift engineering
• Terraform
• Backstage/IDP
• Continuous delivery, observability (inc. metrics/telemetry/SLO/run book automation)
• Platform engineering, control engineering