Description

You will own the engineering of the machine learning platform supporting model deployment and optimization on AWS.

This role is on-site.

Responsibilities

• Assess existing ML models and infrastructure for migration to AWS SageMaker.
• Design and implement migration strategies from on-premises or other cloud platforms to SageMaker.
• Streamline the ML lifecycle using SageMaker services including Pipelines, Studio, Model Registry, and Endpoints.
• Manage ML operations and deployment workflows within the AWS ecosystem.

Required Skills

• 5+ years in ML Engineering or MLOps roles.
• Strong, hands-on experience with AWS SageMaker (Studio, Pipelines, Model Registry, Endpoints).
• Proficiency in Python and containerization using Docker.
• Experience with Terraform for infrastructure management.
• Working knowledge of AWS services including S3, ECR, Lambda, and IAM.
• Experience migrating ML models to AWS SageMaker.
• Familiarity with MLOps principles and Gen AI concepts.

Key Skills

Education

Any Graduate