Hi, I’m Mirza Klimenta. I hold a PhD in Computer Science from the University of Konstanz and work as a Senior Data Scientist focusing on LLMs/RAGs, Recommender Systems, Knowledge Graphs and Classical ML.
Hi, I’m Mirza Klimenta. I hold a PhD in Computer Science from the University of Konstanz and work as a Senior Data Scientist focusing on LLMs/RAGs, Recommender Systems, Knowledge Graphs and Classical ML. I design and deploy production-ready models, including a recommender system powering ARD Audiothek, Germany’s popular audio-on-demand platform.
In parallel with research, I contribute to open-source projects, publish on graph drawing and ML topics, and I’m also a writer of literary fiction, with a novel titled Waters of the Green. I enjoy bridging academia and industry to solve real-world problems.
Objective: To foster communication among like-minded users through dynamic
group formation based on their responses to specific questions.
Approach: Employed vectorization and K-Nearest Neighbors (KNN) for initial grouping,
with a recommendation system for refined group alignment.
Objective: To advise individuals on financial actions that enhance their chances of
achieving specific goals.
Context: For an Asian bank aiming to offer actionable advice for long-term financial
planning, such as securing a home purchase in 20 years.
Approach: Predictive machine learning models were developed to suggest optimal
actions (example: obtaining a salary increase of at least 10%).
Objective: To surpass the performance of Amazon Personalize’s Hierarchical Recurrent
Neural Network-based recommendation system.
Approach: Adopted a recommender model based on Factorization Machines, significantly
improving recommendations through targeted feature engineering.
Objective: To predict the likelihood of loan repayment by bank customers, aiding
in their segmentation for tailored communication strategies (email, SMS, or phone
calls).
Achievement: Created a behavioral scoring machine learning model, now incorporated
into Receeve’s collection approach.
Objective: To forecast investors’ forthcoming decisions on company investments.
Approach: Transformed the challenge into a graph-based problem, treating investors
and companies as nodes. Developed a Graph Neural Network to predict potential
investor-company connections, integrating this model into StockFink’s prediction
suite.
Objective: To predict vehicle transportation prices, providing dispatchers with a
reliable basis for pricing.
Achievements: Enhanced the machine learning model’s accuracy by approximately
40% through advanced feature engineering and implementing a two-tiered regression
strategy, combining residual and standard regression techniques powered by XGBoost.
Objective: To detect unusual behavior in a sensor-monitored network.
Method: Established a baseline machine learning model predicting expected sensor
readings, using deviations from this model to flag anomalies. Enhanced detection
accuracy with a Graph Neural Network, analyzing the connectivity between sensors
and observable areas.
Objective: Fraud detection.
Approach: I designed and developed a fraud detection model for a Middle-Eastern
Buy-Now Pay-Later platform. A critical step for this client involved data preprocessing,
during which I employed a graph-based approach to identify cliques of
fraudsters. This was the first successful machine learning project for this client.
Objective: given a spectral image that depicts the value of the sensors’s readings,
classify the signals and identify novelties (anomalies).
Approach: Given that there was not sufficient labeled data, I had to rely on selfsupervised
machine learning paradigms. To satisfy the customer’s request for fast
processing, I utilized one of the YOLO architectures. The system was developed
with the mmyolo framework.
Objective: an LLM chatbot to help with HR-related inquiries.
Approach: I led the development of an advanced Retrieval-Augmented Generation
(RAG) system aimed at improving HR data retrieval processes. This system utilizes
the Milvus Vector Similarity Search Database and OpenAI’s API to efficiently source
and integrate extensive HR-related data, enabling it to respond to a broad spectrum
of HR inquiries. We have also attempted to fine-tune an LLM for this task, and the
technologies used were PEFT (LoRA), and sophisticated Prompt Engineering.
PulseSpotter is designed to assist journalists in identifying newsworthy topics that are likely to become popular. By gathering information from various news sources and analyzing patterns over time, the system suggests emerging trends using AI and machine learning.
Led development of an advanced Retrieval-Augmented Generation (RAG) system for HR data. Used Milvus vector search, OpenAI API; attempted fine-tuning with PEFT (LoRA); technologies included LangChain, LangGraph, Smolagents, LlamaIndex, dspy; deployed via Terraform and GitHub Actions on AWS; initial Streamlit app.
Senior Data Scientist focusing on LLMs/RAGs, Recommender Systems, Knowledge Graphs and Classical ML; leading projects and delivering production-grade models.
Post a job and invite Mirza, or contact them directly. No hidden commission.
