Description

You will own the deployment, scaling, and lifecycle management of machine learning models, including LLMs, in production environments.

This role is on-site.

Responsibilities

• Design and implement scalable CI/CD pipelines for continuous delivery of ML models.
• Build automation scripts for data preprocessing, model training, and evaluation workflows.
• Develop monitoring solutions to ensure observability and reliability of deployed models.
• Optimize model performance and infrastructure for scalability and efficiency.
• Validate deployments through performance testing to identify and resolve bottlenecks.

Required Skills

• 6+ years of professional experience, with at least 4 years in an MLOps role.
• Expertise in Python for deploying classical and deep learning models.
• Hands-on experience with MLOps frameworks such as SageMaker or Databricks.
• Proficiency with DevOps tools including Docker, Kubernetes, and Terraform.
• Strong command of Git for version control.
• Experience deploying deep learning models in production at scale.
• Ability to manage deployments across AWS, Azure, or Google Cloud.
• Knowledge of SQL, NoSQL, and ETL processes for data pipelines.

Preferred Skills

• Experience deploying GenAI solutions in production environments.
• Familiarity with model hubs and no-code integration platforms like Hugging Face and AWS Bedrock.

Key Skills

Education

Any Gradute