Built Python-based data pipelines using Pandas and SQL to clean, transform, and feature-engineer financial log data for AI/ML
experimentation, enabling faster analysis of risk, bias, and model behavior.
Integrated LLM APIs with prompt engineering and retrieval-augmented generation patterns using LangChain to support large-context
analysis and improve response quality in internal AI workflows.
Designed and evaluated machine learning pipelines using scikit-learn for classification and regression use cases, validating model
performance with standard evaluation metrics and lightweight PyTorch experiments.
Developed RESTful backend services using FastAPI and Flask to expose model workflows, manage JSON data exchange, and
persist benchmarking results for scalable research and testing use cases.
Implemented authentication, logging, error handling, and pytest-based testing to improve service reliability and maintainability across
collaborative engineering environments.
Containerized applications with Docker and supported CI/CD workflows using GitHub Actions, improving deployment consistency and
reducing manual development overhead.
