Software Engineer Intern
GSK · Nov 2024 – Jan 2026
- Contributed to the development of the AI/ML platform, supporting regional deployments and enabling scalable data-driven workflows. • Extracted and integrated structured data from relational databases (SQL), CSV files, and REST APIs, ensuring reliable ingestion and standardized processing. • Performed comprehensive data cleaning, transformation, and validation, improving dataset accuracy and consistency for downstream analytics and ML models. • Optimized complex SQL queries, reducing data retrieval time and improving overall system performance. • Collaborated with the Data Engineering team to design and enhance ETL pipelines for automated data ingestion, transformation, and loading. • Investigated and resolved data inconsistencies within pipelines, improving data integrity,
- Contributed to the development of the Segmentation tool, supporting data extraction and validation processes for Belgium and Greece.
- ◦ Extracted and consolidated data from multiple sources including SQL databases, CSV files, and REST APIs.
- ◦ Performed data cleaning, transformation, and validation to ensure high data accuracy and consistency.
- ◦ Developed FastAPI-based backend services for an AI platform, implementing optimized data retrieval mechanisms using SQL.
- Contributed to LLM-powered solution development, incorporating retrieval-augmented techniques to deliver
- context-aware outputs.
- ◦ Designed scalable API architectures for AI workflows, enabling efficient communication between models and
- data sources.
- ◦ Improved system efficiency by optimizing SQL queries and response pipelines, reducing processing time and
- enhancing user experience.
