Machine Learning/AI Engineer

Internal AI-driven platform designed to automate and standardize repetitive data processing tasks. The system focuses on use cases such as product categorization, context-aware translation, and structured data enrichment.

One of the core components, enables users to configure classification pipelines and upload domain-specific knowledge files. Based on this input, the system processes structured datasets (e.g., Excel files with multiple attributes like category, subcategory, size) and assigns accurate values to each field.

For example, for a given product the system determines the correct classification (e.g., Shampoo instead of Laundry Detergent) using contextual reasoning.

The processing pipeline runs on Databricks (DBR), where dynamic prompt generation and LLM-based inference are used to enrich and classify data at scale. The platform integrates backend services, AI pipelines, and cloud infrastructure to deliver reliable and reusable AI capabilities across business units.