- Enhanced and optimized sequential log anomaly detection algorithm- Currently developing an advanced inference-level Retrieval Augmented Generation system, integrating LLMs (both open-source and proprietary), to address repository-level tasks such as automated code review.

- Focused my research on applying deep generative modelling in Energy Informatics.- Led a project on the application of GANs in energy anomaly detection.- Authored a paper on the findings as first author, which was presented at the AI4TS (Artificial Intelligence for Time Series) workshop at the AAAI 24 (Association for the Advancement of Artificial Intelligence) conference.

- Led projects focusing on multiple areas including Explainable AI and GeneticAlgorithms.- Served as a Teaching Assistant for courses related to Quantitative Analysis, Computational Modelling and Machine Learning.- Actively mentored undergraduate students on their research projects, and guided them in the development and realization of their ideas.-Produced 2 Q1 journal papers, an ACM BuildSys workshop paper, and a Springer book chapter, all as first author.

- Researched and developed advanced deep learning and machine learning solutions specializing in anomaly detection within logs and metrics produced by cloud-native applications- Implemented deep learning techniques including LSTMs, Variational Autoencoders (VAEs), and Normalizing Flows for anomaly detection tasks.- Conducted interviews of the candidates applying for the ML Engineer role.

- Developed a product implementing Latent Dirichlet Allocation (LDA), a probabilistic topic modelling technique, to map functionality scripts to software documentation, enhancing user accessibility and comprehension.- Designed a user interface for the product using Tkinter, enhancing user interaction and overall product usability.