A full-stack AI application featuring RAG, LLM integration, and real-time streaming.
KeyTakes is a full-stack AI application I engineered from the ground up that can summarize any webpage and YouTube video. The system leverages Google's Gemini models to perform complex summarization and analysis tasks. For its interactive Q&A feature, I implemented a Retrieval-Augmented Generation (RAG) pipeline, utilizing vector embeddings and cosine similarity to dynamically fetch relevant context for the LLM.
To perfect user experience during these long-running AI processes, I architected the backend using asynchronous serverless functions on Vercel and streamed results to the Next.js frontend in real-time with Server-Sent Events (SSE). The project also involved building a robust web scraping service with Puppeteer and managing user data and application state with Firebase.
A solo developer project combining AI & UX, with HTML, TailwindCSS, and JS.
I created a browser extension called Dawn with the goal of promoting digital wellness.
Dawn replaces the standard new tab page with a customizable dashboard where users can select and position cards to their liking.
Dawn includes various cards centered around productivity and mindfulness and integrates a Large Language Model (LLM) to enhance its functionality.
This project allowed me to apply my UX, design, and coding skills, primarily using HTML, TailwindCSS, and Javascript.
It further enhanced my skills in working with APIs and asynchronous programming
and offered me an invaluable holistic experience of overseeing an entire development cycle.
Dawn received a "Featured" badge from Google representing its adherence to high standards. Furthermore, a positive user reception, with over 1,000 downloads and a 5-star rating on the Chrome Web Store.
My research on a novel human-AI interaction framework
Sustainable battery solutions
Team dynamics research
I'm an engineer who loves creating innovative solutions by combining AI, software engineering, design, and business insights. With a background in AI, data- and software engineering, and UX, I build intuitive and effective products—whether for consumer or enterprise. My strength is simplifying complex technical challenges into clear, user-friendly solutions that can genuinely improve how organizations operate.
05/2024 – 05/2025
During my year at E-mergo, I embarked on an intensive learning journey, focusing on gaining practical experience and expanding my knowledge in data engineering, AI, and Azure. This period was marked by significant growth, including earning six Microsoft certifications and active involvement in various data engineering and AI-related projects. Ultimately, my deepening passion for AI over traditional data roles led me to seek opportunities more aligned with that focus after this foundational year.
05/2024
Began my role as a Junior Data Engineer, kicking off a year of intensive learning and growth in data, AI, and cloud technologies.
06/2024 – 08/2024
Responsible for optimizing and formalizing internal promotion procedures for Qlik, PlatformManager, TimeXtender, and PowerBI, requiring technical knowledge and strategic process improvement.
07/2024 – 08/2024
Created an AI solution by analyzing data architecture, data sources, exploring business processes, and defining the problem. Developed a business case and a design for a RAG-based LLM system, tailored to their needs, with a PoC in Azure AI Studio and Microsoft AutoGen.
09/2024 – 09/2024
Analyzed Qlik scripts to identify transformations and used data lineage to trace the transformed variables to their corresponding points in TimeXtender. Created new columns, applied SQL-based transformations, and ensured proper integration within the Semantic Layer in TimeXtender.
10/2024 – 10/2024
Helped set up a TimeXtender data warehouse, including configuring servers, databases, APIs, and the TimeXtender environment, using TimeXtender, SQL Server Management Studio (SSMS), and Postman. Cleaned and transformed data using SQL and addressed challenges such as high-volume streaming data, incremental loading, and changing dimensions.
12/2024 – 01/2025
Involved in setting up connections with multiple API endpoints, combining queries, and establishing incremental data loading patterns. Further strengthened PowerBI skills.
AI-102 - Microsoft Certified
Demonstrates the ability to design and implement AI solutions using Azure AI services, Azure AI Search, and Azure OpenAI to meet business needs.
AI-900 - Microsoft Certified
Demonstrates fundamental AI concepts related to the development of software and services of Microsoft Azure to create AI solutions.
DP-203 - Microsoft Certified
Demonstrates understanding of common data engineering tasks to implement and manage data engineering workloads on Microsoft Azure, using a number of Azure services.
DP-900 - Microsoft Certified
Demonstrates foundational knowledge of core data concepts related to Microsoft Azure data services.
AZ-900 - Microsoft Certified
Demonstrates foundational knowledge of cloud concepts, core Azure services, plus Azure management and governance features and tools.
PL-300 - Microsoft Certified
Demonstrates methods and best practices that align with business and technical requirements for modeling, visualizing, and analyzing data with Microsoft Power BI.
My affinity for technology drives my quick adoption of new software, languages, and frameworks—a process I genuinely enjoy.