Kostas P.
Data Science Contractor
Experience
Apr 2025 - Dec 2025
9 monthsAmsterdam, Netherlands
Data Science Contractor
Elsevier
- Created an evaluation pipeline for a RAG system using an LLM-as-a-judge approach, incorporating answer quality metrics such as comprehensiveness and harmfulness, as well as custom reproducibility and consistency metrics.
- Implemented workflow enhancements in the existing RAG system, expanding business case coverage and increasing customer sales by 20%.
- Improved the existing RAG model by adding error-handling branches to ensure a valid answer is always returned.
- Collaborated with subject matter experts to design evaluation datasets for key components of the pipeline, including question rephrasing, document retrieval, and answer generation.
Jan 2024 - Apr 2025
1 year 4 monthsAthens, Greece
Data Scientist
Synthetica
- Developed a RAG-based agent system for complex files (PDF, Word, scanned images, often multilingual) that accurately retrieved and generated relevant information for users. The document format was highly unstructured, containing figures, tables, and scanned pages. To handle this complexity, OCR, segmentation, and vision LLM models were employed.
- Fine tuned an embedding model with a custom dataset and labels achieving higher accuracy compared to the baseline with HuggingFace on a multi-GPU set-up.
- Operated in an agile environment with bi-weekly sprints and regular daily/weekly meetings.
- Utilized Docker to deploy models and APIs, and employed Kubernetes to manage Google Cloud resources.
May 2022 - Jan 2024
1 year 9 monthsAthens, Greece
Data Scientist
Synelixis Solutions
- Implemented an intrusion detection system (IDS) trained within a federated learning framework, achieving an F1-score of 95% in malicious packet detection using TensorFlow and TensorFlow-Federated.
- Developed a local style transfer technique using Facebook’s Segment Anything Model achieving visually captivating results.
- Employed common software engineering tools and frameworks such as Docker and FastAPI/Flask to ensure that the projects can be reused efficiently, along with the version control system Git in all implementations.
Aug 2021 - May 2022
10 monthsAthens, Greece
Data Scientist
Alexander Moore
- Collaborated with two other engineers to implement a sales forecasting system that accurately predicted weekly sales quantities for over 100 products using statsmodels, scikit-learn, and Keras.
- Developed an NLP-based sentiment analysis module utilizing TensorFlow and NLTK that achieved a 90% accuracy rate in classifying customer comments in real-world scenarios.
- Built and deployed a churn prediction model that was able to classify users correctly and reduced the client’s operational cost by 20%.
Languages
Greek
NativeEnglish
AdvancedGerman
IntermediateEducation
Oct 2015 - Jun 2021
National Technical University of Athens (NTUA)
Master of Engineering, Electrical and Computer Engineering · Electrical and Computer Engineering · Athens, Greece
Need a freelancer? Find your match in seconds.
Try FRATCH GPT More actions
Similar Freelancers
Discover other experts with similar qualifications and experience
- English
- Deutsch
2025 © FRATCH.IO GmbH. All rights reserved.