Production ML Engineer: Pipelines & Observability

Nexum AI is seeking a Machine Learning Engineer to turn models and experiments into reliable, observable and maintainable production systems. You will connect data, training, deployment and operations while preserving reproducibility and traceability.

What you will do: Design pipelines, package models as secure, tested services, establish versioning, automate validation and deployment across cloud and Kubernetes, and monitor performance and data drift.

Design and implement data, feature, training, validation and deployment pipelines Package models as secure, tested and versioned services or batch workloads Establish versioning and lineage for code, data, configurations and model artifacts Automate model validation, CI/CD and controlled deployment across cloud and Kubernetes environments Monitor prediction quality, latency, throughput, resource usage, failures and data or model drift Investigate production issues and improve reliability, performance and operating cost Collaborate with Data Scientists, AI Engineers, DevOps and platform teams on clear production acceptance criteria Experience building data and model pipelines in production. Ability to train/validate and version ML artifacts. Experience with Docker, Kubernetes, and cloud services. Familiarity with CI/CD and observability practices.