Baris
Soybas

• Built secure RESTful APIs with FastAPI, SQLAlchemy, Pydantic and Alembic migrations, backed by SQL Server.
• Designed Next.js frontends with JWT & OAuth flows — integrating LLM-powered interfaces and interactive visualizations delivered up to the C-level.
• Trained and deployed scikit-learn / MLflow models to predict costs & premiums and classify transactions, backed by EDA and data visualizations created by pandas/NumPy, plotly & matplotlib.
• Prototyped a Text-to-SQL chatbot with LangChain and vector databases — natural-language querying of internal business data.
• Defined branching, testing & CI/CD strategies for dockerized apps across three Azure Kubernetes environments under regulatory compliance.
• Set the team's technical stack and coding standards — reused across multiple applications and projects.
• Mentored working students and junior team members and conducted interviews for technical roles.

A single entry point that brings the team's finance dashboards and internal applications under one roof — pairing a curated landing page with centralised authorisation and user management for everyone working in the finance domain.

Generates analyst commentary on individual Profit & Loss positions (GuV) by feeding curated financial data into an Azure OpenAI model — turning line-item numbers into draft narratives ready for review.

Computes statutory claims and equalisation reserves (Schadenreserve & Schwankungsrückstellung) for German insurance reporting, paired with an interactive dashboard that surfaces the underlying drivers and year-over-year fluctuations.

Thesis — Implementation of artificial intelligence in assistance systems for the digitalization of production processes, with Heimbach GmbH and the Institute of Textile Technology.

Thesis — Integration of a 3.3 MW generator into the 850 kW drivetrain of a wind turbine, at the Chair for Wind Power Drives.

Internship — Implementation of Intralogistics 4.0 in manufacturing at Bosch Rexroth AG, Stuttgart.