Senior Machine Learning Engineer – AWS SageMaker

Cloudworkz is seeking a Senior Machine Learning Engineer with strong hands-on experience in Amazon SageMaker, tabular machine learning and model explainability.

You will build and validate classification models for an enterprise order-tolerance management solution, helping business users understand recommendations for resolving order-tolerance issues. You will work closely with cloud and application engineers to deliver reproducible machine-learning workflows and clear, usable prediction outputs.

WHAT YOU WILL DO

• Prepare, clean and validate model input data stored in Amazon S3.

• Develop tabular classification models using XGBoost and/or LightGBM.

• Implement robust model validation, probability calibration and SHAP explainability.

• Build workflows using SageMaker Processing, Training, Pipelines, Model Registry, Batch Transform and Clarify.

• Integrate Amazon Bedrock to turn model recommendations into plain-language explanations for business users.

• Collaborate with the application engineer on prediction outputs and application integration.

• Produce reproducible code and documentation using the agreed infrastructure and CI/CD tooling.

• Apply lightweight, practical MLOps appropriate to a non-production solution build.

• Document evaluation and calibration results, model versions, explainability outputs and integration guidance.

WHAT YOU WILL BRING

• Proven personal ownership of tabular ML delivery on Amazon SageMaker, supported by concrete project examples.

• Strong Python skills and practical experience preparing and validating data on Amazon S3.

• Hands-on XGBoost and/or LightGBM modelling experience.

• Practical experience with model validation, probability calibration and explainability, including SHAP.

• Hands-on use of SageMaker Processing, Training, Pipelines, Model Registry, Batch Transform and Clarify, including batch inference and model registration.

• The ability to explain your own implementation responsibilities, dataset and model scale, and measured outcomes clearly.

• Strong collaboration and communication skills when working with application engineers and business stakeholders.

TECHNOLOGY ENVIRONMENT

AWS, Python, Amazon SageMaker, Amazon S3 and Amazon Bedrock, with Terraform, Azure DevOps CI/CD, Docker and Amazon ECR. The wider environment also uses Microsoft Entra ID. Experience with these supporting tools is useful.

WORKING ARRANGEMENTS

Remote within EMEA.

WHEN APPLYING

Please include examples of tabular ML projects you personally delivered on Amazon SageMaker. For each, describe:

• The SageMaker services used and your own implementation responsibilities.

• Dataset scale and the classification problem addressed.

• Your validation approach, probability calibration and explainability work.

• Batch-inference and model-registration workflows.

• Measured outcomes and the lessons learned.

Project examples should demonstrate direct ownership of the core SageMaker and tabular ML work.