What you'll do:

• Model Deployment: Deploy machine learning models in production environments on cloud platforms such as Azure and AWS. Work closely with data scientists and software engineers to integrate models into existing systems.
• Infrastructure Management: Set up and maintain infrastructure for machine learning model deployment. Ensure smooth integration of ML workflows into CI/CD pipelines.
• Monitoring and Maintenance: Implement and manage robust monitoring solutions to track model performance, data drift, and other relevant metrics. Proactively identify and address issues related to model degradation or system failures.
• Cloud Expertise: Demonstrate expertise in cloud platforms, particularly Azure and/or AWS, for deploying and managing machine learning services.
• Automation and Scripting: Develop automation scripts and tools to streamline deployment processes and enhance efficiency. Implement infrastructure as code (IaC) practices for reproducibility and scalability.

What makes you a great fit:

• Experience: 5-8 years of hands-on experience in deploying and monitoring machine learning models.
• Basic understanding of ML and data science/modeling aspects.
• Proficiency in cloud platforms, especially Azure and/or AWS.
• Experience with open-source tools for MLOps, such as Kubernetes, Docker, and Apache Airflow and developing and streamlining workflows, building scalable pipelines, etc.
• Ensuring successful model development, testing, optimization, scaling, monitoring/observability, and governance.
• Continuous integration and continuous deployment (CI/CD).
• Knowledge of best practices and processes to promote reproducibility in a centralized manner (cloud/hybrid infrastructure and environment).
• Strong scripting skills (e.g., Python) for automation and tool development.
• Strong problem-solving skills with a focus on finding efficient and scalable solutions.
• Ability to learn new tools on the go and developing best practices is mandatory.