As a Machine Learning Engineer at Accenture, I contribute to the development and implementation of cutting-edge Computer Vision and Generative AI solutions.
Download CV
Hi, I’m a Machine Learning Engineer based in Munich, Germany, passionate about turning data and algorithms into intelligent, and real-world solutions. Over the past few years, I’ve worked on a wide range of projects, from constrained optimization for neural networks at Bosch (which led to a patent 🎉) to AI-powered solutions in supply chain and predictive analytics at companies like Aioneers, TopSeven, and Accenture. My toolkit includes Python, Generative AI, Agentic AI, and Azure, and I’m always exploring new technologies that make AI systems more reliable, scalable, and explainable.
VoltAssist is a simple Streamlit RAG-based Chatbot for supporting customer of e-commerce electronics stores. It can be an accelerator for a RAG-based chatbots, specifically for automating FAQs and question-answering.
AskHR is a simple Streamlit app that demos how a chatbot can be build with Large Language Models (LLMs). It works with synthetic policy data, department/level selectors, and chat history. It has also functionality like starter chats and contact support button. Here you will find the structure and guidelines how to use it.
A tool for loading UCI Machine Learning Repository datasets easily without need to download them.
This is the companion code for the Master Thesis entitled "". The master thesis is done in Bosch Center of AI research, and licenced by GNU AFFERO GENERAL PUBLIC LICENSE. The code allows the users to apply constrained for one type of error, such as false negative rate to do safe classification using gradient boosting. Besides, one can reproduce the results in the paper as it is provided in the examples.
VoltAssist is a simple Streamlit RAG-based Chatbot for supporting customer of e-commerce electronics stores. It can be an accelerator for a RAG-based chatbots, specifically for automating FAQs and question-answering.
AskHR is a simple Streamlit app that demos how a chatbot can be build with Large Language Models (LLMs). It works with synthetic policy data, department/level selectors, and chat history. It has also functionality like starter chats and contact support button. Here you will find the structure and guidelines how to use it.
A tool for loading UCI Machine Learning Repository datasets easily without need to download them.
This is the companion code for the Master Thesis entitled "". The master thesis is done in Bosch Center of AI research, and licenced by GNU AFFERO GENERAL PUBLIC LICENSE. The code allows the users to apply constrained for one type of error, such as false negative rate to do safe classification using gradient boosting. Besides, one can reproduce the results in the paper as it is provided in the examples.
Attention network is the core of Transformers, Vision Transformers, and Large Language Models (LLMs). Understanding the Attention mechanism and the neural architecture of the attention network helps to understand the transformers architecture and the LLMs much better.
Transformers opened a new door through Natural Language Processing, and it is the basis of LLMs, which outperforms the earlier NLP models such as RNN. Google introduced Transformers in 2017 in the paper entitled: Attention is all you need. In this tutorial, I tried to explain the architecture based on the Google paper in a simpler way.
Attention network is the core of Transformers, Vision Transformers, and Large Language Models (LLMs). Understanding the Attention mechanism and the neural architecture of the attention network helps to understand the transformers architecture and the LLMs much better.
Transformers opened a new door through Natural Language Processing, and it is the basis of LLMs, which outperforms the earlier NLP models such as RNN. Google introduced Transformers in 2017 in the paper entitled: Attention is all you need. In this tutorial, I tried to explain the architecture based on the Google paper in a simpler way.
Safe contextual Bayesian optimization integrated in industrial control for self-learning machines
Safe contextual Bayesian optimization integrated in industrial control for self-learning machines
VoltAssist is a simple Streamlit RAG-based Chatbot for supporting customer of e-commerce electronics stores. It can be an accelerator for a RAG-based chatbots, specifically for automating FAQs and question-answering.
AskHR is a simple Streamlit app that demos how a chatbot can be build with Large Language Models (LLMs). It works with synthetic policy data, department/level selectors, and chat history. It has also functionality like starter chats and contact support button. Here you will find the structure and guidelines how to use it.
A tool for loading UCI Machine Learning Repository datasets easily without need to download them.
This is the companion code for the Master Thesis entitled "". The master thesis is done in Bosch Center of AI research, and licenced by GNU AFFERO GENERAL PUBLIC LICENSE. The code allows the users to apply constrained for one type of error, such as false negative rate to do safe classification using gradient boosting. Besides, one can reproduce the results in the paper as it is provided in the examples.
VoltAssist is a simple Streamlit RAG-based Chatbot for supporting customer of e-commerce electronics stores. It can be an accelerator for a RAG-based chatbots, specifically for automating FAQs and question-answering.
AskHR is a simple Streamlit app that demos how a chatbot can be build with Large Language Models (LLMs). It works with synthetic policy data, department/level selectors, and chat history. It has also functionality like starter chats and contact support button. Here you will find the structure and guidelines how to use it.
A tool for loading UCI Machine Learning Repository datasets easily without need to download them.
This is the companion code for the Master Thesis entitled "". The master thesis is done in Bosch Center of AI research, and licenced by GNU AFFERO GENERAL PUBLIC LICENSE. The code allows the users to apply constrained for one type of error, such as false negative rate to do safe classification using gradient boosting. Besides, one can reproduce the results in the paper as it is provided in the examples.
Let’s connect! Fill out the form and I’ll be in touch soon.
