Ірина

KATANA IRYNA
JUNIOR MACHINE LEARNING ENGINEER

CONTACT SUMMARY
Highly motivated Junior ML engineer with a strong
MOBILE: [open contact info](look above in the "contact info" section) foundation in developing machine learning models for
different purposes. Have experience in Prompt Engineering
TELEGRAM: https://t.me/kogarashiiiii
for enhancing the efficiency of different processes.
EMAIL: [open contact info](look above in the "contact info" section) Proficient in Python and C(++), and skilled in leveraging
libraries like TensorFlow, Keras, and Pandas to achieve
LINKEDIN: [open contact info](look above in the "contact info" section) high-quality outcomes. Has good communication skills, and
is a highly responsible, flexible, and active individual.
ADDRESS: Kyiv, Remote

EXPERIENCE Feb 2024 -
SKILLS JUNIOR PROMPT ENGINEER | GOIT Present

In my role as a Prompt Engineer at GoIT, I was
PROGRAMMING LANGUAGES
responsible for optimizing the homework review process
Python through the development and implementation of AI-
Java driven tools, utilizing the OpenAI API. My primary focus
C++ was on improving efficiency and accuracy in educational
assessments, namely:
DATABASE MANAGEMENT SYSTEMS
Developed automated solutions for checking
MySQL homework assignments, focusing on creating,
SQLite testing, and refining AI-driven prompts.
ArangoDB Analyzed complex homework requirements to
MongoDB identify opportunities for automation that contribute
to more efficient learning processes.
ML/AI-RELATED Worked collaboratively with educators and students
OpenAI API to collect and analyze feedback, which is used to
ChatGPT improve the accuracy and functionality of the
Tensorflow prompts.
Keras Suggested and implemented modifications to
Pandas educational content to better accommodate AI-
Machine Learning driven automation, facilitating easier and more
effective future integrations.
Convolutional Neural
Achievements:
Network Computer Vision
Developed prompts that enabled the company to
Natural Language Processing
save over 60,000 UAH per month.
Time Series Forecasting
Optimized prompts, significantly enhancing their
RNNs accuracy and reducing the need for manual edits to
GRUs AI responses.
LSTMs
Augmentation
Transfer Learning EDUCATION
BACHELOR OF COMPUTER SOFTWARE ENGINERING
FRAMEWORKS
Django Zaporizhzhya National University
AngularJS 2021-present

OTHER
LANGUAGES
Git, JSON, XML, HTML/CSS
English - Upper-intermediate
Ukrainian - Native speaker
PROJECTS

HANDWRITING RECOGNITION SNAKE GAME REINFORCEMENT
SYSTEM Jan 2024 LEARNING Nov 2023

Description: I have successfully developed a highly Description: This project aimed to develop a Snake
accurate handwriting recognition system that is game trainer using reinforcement learning techniques
capable of interpreting handwritten words using the powered by artificial intelligence. To achieve this, a
IAM dataset. The system implements a Convolutional Snake game environment was created, followed by an
Neural Network (CNN) with Long Short-Term Memory agent that was trained using a linear Q-learning neural
(LSTM) layers and a Connectionist Temporal network architecture. The neural network consisted of
Classification (CTC) loss function, which is perfect for 11 input neurons, 256 hidden neurons, and 3 output
text recognition tasks. After thorough training for more neurons. The inputs provided essential information
than 200 epochs, the model was tested on a sample of such as the snake's spatial orientation, trajectory, and
the validation data and saved for future use. The proximity to potential hazards and rewards. During the
system was implemented using the Python training process, the agent learned to make decisions
programming language, TensorFlow framework, and on the next move by maximizing its expected
custom mltu library, achieving high accuracy rates in cumulative reward. This was achieved through
text recognition tasks. The project involved meticulous iteratively playing the game, observing the outcomes,
data preprocessing, model training, and evaluation, and updating the agent's policy to improve its
resulting in a robust system that can accurately performance. The model's performance steadily
recognize a wide range of handwriting styles. increased from 0 to 58 over 100 iterations.

Tools&Technologies: Python, TensorFlow, Keras, Tools&Technologies: Python, Anaconda, PyTorch,
Machine Learning, CNNs, Image Processing, VS Code Pygame, Machine Learning, Reinforcement Learning,
VS Code

E-LIBRARY Sept 2023 SCIJOURNAL MANAGER Apr 2023

Description: The E-library management system is a Description: SciJournal Manager is a desktop
digital solution that efficiently manages library application designed for science journal management.
resources and users. It is designed to streamline and It facilitates seamless article submissions, ensuring
organize routine operations related to preserving and each submission includes at least one author, two
providing access to library resources. This system abstracts (in English and Ukrainian), keywords, and a
covers several aspects, such as managing the book full-text file stored securely on a server. The system
inventory, automated registration of book issuance automates the assignment of two reviewers per
and returns, and provides a user-friendly interface for article, who evaluate submissions on several criteria,
interaction between library staff and readers. providing ratings and detailed reports for editorial
Tools&Technologies: Python, JavaScript, Django, consideration and author feedback.
AngularJS, HTML/CSS, SQLite, VS Code Tools&Technologies: Python, ArangoDB, VS
Professional, Arango Shell, Arango Management
(web) Interface

CERTIFICATIONS
DEEPLEARNING.AI TENSORFLOW DEVELOPER

DeepLearning.AI on Coursera
June 2023 - Aug 2023

INTRODUCTION TO TENSORFLOW FOR ARTIFICIAL INTELLIGENCE, MACHINE LEARNING, AND DEEP LEARNING

CONVOLUTIONAL NEURAL NETWORKS IN TENSORFLOW

NATURAL LANGUAGE PROCESSING IN TENSORFLOW

SEQUENCES, TIME SERIES AND PREDICTION