Olga Seleznova

Olga Seleznova

About

Detail

Canada
Contact Olga regarding: 
connect_without_contact
Finding mentors
Finding co-founders
groups
Networking

Timeline

work
Job
school
Education
folder
Project

Résumé

Jobs verified_user 0% verified
  • D
    Data Scientist (volunteering)
    Data for Good
    Mar 2025 - Apr 2025 (2 months)
    - Designed and implemented an end-to-end NLP pipeline for multilingual survey analysis, including translation, summarization, sentiment classification, and keyword extraction to surface key insights.
    - Built a RAG-based chatbot using LangChain and OpenAI API to enable interactive exploration of company PDFs.
    - Documented the entire workflow to support reproducibility and cross-functional collaboration.
    - Utilized UX/UI skills by employing Streamlit to create an intuitive interface, allowing stakeholders to interact seamlessly with the NLP pipeline and RAG-based chatbot, enhancing user experience and engagement.
  • V
    Data Scientist
    VoxTour.ai
    Feb 2025 - Current (1 year 9 months)
    • Operate within a live deployment environment, simulating production conditions to troubleshoot effectively and enhance system performance.
    • Follow Test-Driven Development (TDD) practices to write robust, maintainable code in Kotlin, ensuring high test coverage and reliable system behavior.
    • Test and refine prompts to ensure creative consistency and optimal performance of AI models in producing engaging narratives.
    • Engaged in API management and integration while operating in a live deployment environment, interacting with APIs to test and refine system behavior under production-like conditions, which contributed to the overall reliability and performance of the system.
  • Technion
    Machine Learning Researcher
    Technion
    Mar 2023 - Jun 2024 (1 year 4 months)
    • Developed over 4 clean and reusable packages in Pytorch for academic purposes by creating templates and streamlining submission processes.
    • Managed virtual machines and created server and Docker environments to support deep learning projects, ensuring a functional and expandable infrastructure, which included basic API integration for resource monitoring and data handling.
    • Operated within the research laboratory, researched automatic speech recognition, performed wave restoration, and audio alignment with text.
  • Skai
    Data Scientist
    Skai
    Sep 2021 - Sep 2022 (1 year 1 month)
    • Delivered actionable insights from large datasets of unstructured reviews to management, facilitating data-driven decision-making and enhancing strategic product development based on customer feedback. • Conducted the research, development, and implementation of advanced NLP systems, including the fine-tuning and error analysis of BERT models for text classification and T5 for question-answering tasks. • Leveraged cloud environments with AWS S3 and EC2 to efficiently store and process large datasets, enabling seamless fine-tuning of NLP models. • Performed within a multidisciplinary team of Python and R developers and data analysts under a product manager's guidance to achieve project deliverables and ensure compliance with technical stan
  • T
    Data Science Intern
    TRG Customer Solutions
    Feb 2021 - Jul 2021 (6 months)
    • Fine-tuned the DistilBERT model from HuggingFace, increasing sentiment classification accuracy from 47% to 86.20% across three categories (positive, negative, and neutral). • Implemented text classification models, including Random Forest, CatBoost, XGBoost, and BERT, utilizing Scikit-learn and Transformers packages to enhance predictive accuracy and performance. • Delivered a comprehensive presentation of findings to students and lecturers, communicating technical details and insights. • Collaborated closely with team members and operated under the guidance of a senior data scientist, efficiently sharing responsibilities and contributing to team success.
  • University of Haifa
    Researcher
    University of Haifa
    Aug 2020 - Dec 2020 (5 months)
    - Contributed to a published paper on informativeness versus emotionality in medical forums, identifying key features to differentiate between these concepts within the Integrative Pain (iPain) laboratory.
    - Achieved approximately 85% accuracy in classifying Hebrew posts from medical forums, addressing low-scale, unbalanced data challenges.
    - Conducted comprehensive EDA, text preprocessing, and classification using Python libraries, including Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn, and PyTorch transformers.
Education verified_user 0% verified
  • Y
    School of Data Science
    YData
    Jan 2020 - Jan 2021 (1 year 1 month)
    - Y-DATA is an intensive one-year career advancement program in Data Science that bridges the gap between short-term online courses and a full-time MSc-level program.
    - Relevant courses: Python for Data science (NumPy and PyTorch), Statistics, Supervised and Unsupervised Machine learning, Deep learning, NLP, Large scale ML (PySpark, SQL).
  • University of Haifa
    Master's Degree
    University of Haifa
    Jan 2018 - Jan 2022 (4 years 1 month)
    - Relevant courses: Data processing (Python), Python for Data science, quantitative methods (statistics), information retrieval, social network analysis, sentiment analysis in text, predictive models, introduction to machine learning.
    - Thesis in Supply chain management and Machine learning.
  • K
    Master of Arts
    Kyiv National Linguistics University
    Jan 2014 - Jan 2015 (1 year 1 month)
  • B
    Bachelor of Arts
    Black Sea State University
    Jan 2008 - Jan 2012 (4 years 1 month)
Projects (professional or personal) verified_user 0% verified
  • J
    Job Posting Relevance
    Jul 2024 - Oct 2024 (4 months)
    An AI-powered tool designed to determine how relevant a job posting is to a candidate's resume. The system leverages the RAG methodology and agentic flow, based on the Langchain framework to analyze how well a resume aligns with the specific requirements of a job posting. Data was managed using MongoDB and user experience was enhanced with the Streamlit application. Additionally, I integrated external APIs within the Streamlit application to enhance interactivity and automate data retrieval, further improving the overall functionality and user engagement of the tool. Link: github.com/OlgaSeleznova/JobPostingRelevancy
  • V
    VoyageVocab Project: Language Learning Assistant for Travellers
    May 2024 - Jul 2024 (3 months)
    Developed an application utilizing Llama and LangChain to generate travel-related phrases for tasks such as ordering food or buying tickets, with a user-friendly interface implemented through the Gradio package. Additionally, I leveraged UX/UI principles by using Gradio to create an interactive front end that allows users to input travel scenarios and receive AI-generated phrase suggestions in real time. Link: github.com/OlgaSeleznova/VoyageVocab