Description

You will build generative AI solutions using Python and Databricks to process multi-modal data, manage vector databases, and deploy cloud-based APIs.

This role is hybrid.

Responsibilities

• Build Python modules to extract content from PDF, DOCX, PPTX, audio, and video formats.
• Implement data processing workflows in Databricks to execute Python code and manage orchestration.
• Manage data chunking, embedding processes, and integration with Vector Databases.
• Develop API calls and create functional API endpoints for generative AI models.
• Execute code deployment to the cloud using CI/CD pipelines.

Required Skills

• 5+ years of experience in software development or data engineering.
• Extensive hands-on experience with Python and its core packages.
• Proficiency with Databricks and its workflow orchestration features.
• Practical knowledge of Gen AI, including chunking and embedding techniques.
• Experience working with Vector Databases.
• Understanding of API endpoint creation and management.
• Knowledge of cloud deployment and CI/CD pipelines for code builds.

Preferred Skills

• Experience with Snowflake.
• Proficiency in SQL.

Key Skills

Education

Any Graduate