THESIS: A comprehensive analysis of cross-platform machine learning runtimes on mobile applications

High level descriptionToday, the most common way to develop cross-platform mobile apps is through frameworks like React Native, Flutter, or Kotlin Multiplatform. Each of these frameworks employs different strategies to build applications for both Android and iOS. However, they share a common limitation: any change— whether it's a minor text update or a new...

High Level DescriptionA common problem in high traffic systems is scaling. When applications take a long time to initialize, scaling in the middle of a traffic spike can cause a noticeable latency impact and even causing downtime. Predictive scaling together with machine learning involves gathering and utilizing data to accurately forecast incoming spikes...

High level descriptionData engineering is the process of refining raw data into a usable state. For example, transforming raw CSV or JSON files into structured formats ready for analysis. There are many platforms and tools available to support this process, each with different trade-offs in terms of performance, scalability, and usability. This thesis will...

High level descriptionModern data engineering faces unprecedented challenges as organizations increasingly deploy IoT devices and edge computing infrastructure that generate massive volumes of distributed data.Traditional centralized data processing approaches struggle with the latency, bandwidth, and reliability constraints inherent in edge-to-cloud data...

High level descriptionWith the rising popularity of AI agents, Anthropic has developed a new protocol for LLM models to communicate with tools. The Model Context Protocol (MCP) is slowly becoming a standard for developing tools for LLMs and LLM Agents. In MCP there are no security or authentication methods, so exposing tools towards end users can be harmful...

High level descriptionThis thesis focuses on evaluating different predictive maintenance models using provided industrial datasets. The goal is to determine which models are most effective in predicting failures and enabling proactive maintenance. The study will compare approaches such as anomaly detection, time-series forecasting, and classification-based...

High level descriptionThis thesis focuses on evaluating different predictive maintenance models using provided industrial datasets. The goal is to determine which models are most effective in predicting failures and enabling proactive maintenance. The study will compare approaches such as anomaly detection, time-series forecasting, and classification-based...

High level descriptionWith the rising amount of AI agents (ChatGPT, OpenAI, Grok, Microsoft CoPilot, Google Gemini, …), it becomes more difficult to know which AI agent to use in different contexts. Some agents might not be fact based enough with no access to real time data, others are easily manipulated by the user, others might provide propaganda due to...

High level descriptionInfrastructure as Code (IaC) is a cornerstone of modern software development and cloud operations. Terraform is one of the most widely adopted tools for provisioning and managing infrastructure across cloud providers, while is a newer framework with a developer-centric focus, combining infrastructure and application logic in a single...

BackgroundIn today's digital landscape, services and offerings are increasingly composed of multiple interconnected applications and systems. This complexity makes it difficult to trace which services are tied to a specific customer identifier and to detect issues such as failed orders or recurring system errors.Traditionally, support and operations teams...