Avatar

Agnieszka Mikołajczyk-Bareła

PhD & Senior AI Engineer

Chaptr.AI

Resume

Researcher, programmer and AI expert with a solid experience in the industry. Currently working as a Senior AI Engineer at Chaptr.AI, developing large language models and AI assistants. Previously, as NLP Team Leader at Voicelab.AI, led the team that designed and trained TRURL, the first ChatGPT alternative in Poland. Successfully defended PhD at Gdańsk University of Technology on detecting and reducing the impact of errors and biases in AI data and models.

With over 2500 citations on Google Scholar, Dr. Mikołajczyk has contributed to numerous research projects and publications in machine learning, focusing on bias detection, explainable AI, and natural language processing. She has led multiple AI for Good initiatives, including HearAI for sign language recognition and DetectWaste for environmental applications.

Interests

  • Large Language Models
  • Explainable Artificial Intelligence
  • Bias Detection & Mitigation
  • Image Analysis
  • Deep Learning

Education

  • PhD in Machine Learning, 2017 - 2022

    Gdańsk University of Technology

  • MEng in Control Theory, 2016 - 2017

    Gdańsk University of Technology

  • BSc in Automation Control and Robotics, 2012 - 2016

    Gdańsk University of Technology

Skills

Python

Langchain, PyTorch, Transformers

Natural Language Processing

LLMs, Transformers, BERT, GPT, RAG

Computer Vision

CNNs, Vision Transformers, Object Detection

AI Assistants

LLM-based agents, Conversational AI, RAG

Experience

 
 
 
 
 

Senior AI Engineer

Chaptr.AI

Nov 2023 – Present Remote
  • Working with AI assistants, LLMs, and LLM-based agents
  • Implementing RAG (Retrieval Augmented Generation) systems
  • Currently focused on book metadata optimization projects
 
 
 
 
 

ML Expert

Designbotic

Mar 2023 – Aug 2023 Sopot, Poland
  • Assisted in developing an AI application for architectural studios
  • Worked on image classification with custom CNNs (PyTorch, ONNX)
 
 
 
 
 

ML Expert

Zatoichi

Mar 2022 – Sep 2022 Warsaw, Poland
  • Assisted in developing an AI application for detecting and reading product expiry dates
  • Designed algorithms to help blind and visually impaired people
  • Worked on detection and OCR using PyTorch and OpenCV
 
 
 
 
 

NLP Team Leader

VoiceLab.AI - Conversational Intelligence

Dec 2021 – Nov 2023 Gdańsk, Poland
  • Led NLP team in R&D Lab working with speech transcripts and natural conversations
  • Designed and prepared training pipelines, data, trained and tested models (transformers, T5, BART, GPT)
  • Led the team that created TRURL.AI, the first ChatGPT alternative in Poland
  • Responsible for training and developing vlT5 model for keyword generation (TOP1 model on HuggingFace)
  • Managed over 40 private models on HuggingFace
 
 
 
 
 

Machine Learning Researcher

VoiceLab.AI - Conversational Intelligence

Mar 2020 – Nov 2021 Gdańsk, Poland
  • Initially worked in ASR team on voice style transfer
  • Later focused on NLP for telephone conversations
  • Developed solutions for punctuation restoration, sentiment analysis, topic modeling, intent recognition, NER, and keyword generation
 
 
 
 
 

Research Intern at Explainable Artificial Intelligence Center

Ulsan National Institute of Science and Technology

May 2019 – Jun 2019 Ulsan, South Korea
 
 
 
 
 

Research assistant

Gdańsk University of Technology

Jun 2018 – Present Gdańsk, Poland
 
 
 
 
 

Research Assistant and C++ Software Developer

Institute of Electrical Engineering

Jul 2014 – Nov 2016 Gdańsk, Poland
 
 
 
 
 

Junior Electromagnetic Compability Engineer

Institute of Electrical Engineering

Jul 2013 – Aug 2013 Gdańsk, Poland

Activities

Presentations & Talks

Conference Presentations

  • The chatbots of tomorrow: Agentic Design Patterns in LLMs (May 22, 2024)
    DATAMASS STAGE, Infoshare event
    View details

  • HearAI: Towards Deep learning-based Sign Language Recognition (October 6, 2022)
    ARENA STAGE, Infoshare event
    See presentation details

Example Video Presentations

  • GenAI bez tajemnic
    An exploration of generative AI topics in a non-technical way
    Watch on YouTube
  • Automated Generation of Keywords from the NLP Perspective
    A presentation on using NLP techniques for keyword generation
    Watch on YouTube

Panel Discussions

  • LLM Use Cases in Production Panel
    MLOps Community panel discussion on large language models in production
    Watch the panel discussion

Awards & Honors

  • Nominated as Top 10 Women in Data Science Poland (2024)
  • Over 2500 citations on Google Scholar as of 2024
  • Senior AI Engineer at Chaptr developing large language models (2023-present)
  • Nominated as Top 100 Women in AI Poland (2023)
  • Co-creator of “the Keygen” newsletter about artificial intelligence, leading the “Explained” section
  • Named among Top Women in AI in Poland (2023)
  • Named one of the “23 Most Influential Poles in AI” by My Company Polska magazine (2023)
  • NLP Team Leader at Voicelab.AI who led the team that developed TRURL.AI, the first ChatGPT alternative in Poland (2023)
  • ML Expert for “Susana” project aimed at detecting and reading product expiration dates to help the blind “see”
  • ML Expert for “Next Designer” architectural project using AI for automatic building plan generation
  • Co-organizer of PolEval 2022 and co-creator of the Polish Corpus for Punctuation Prediction
  • Principal Investigator for “Detecting and overcoming bias in data with explainable artificial intelligence” (Preludium Grant)
  • Organizer and team member of AI for Good educational project HearAI - Modelling Sign Language with Deep Learning
  • Principal ML Researcher for HearAI project working with Vision Transformers, CNNs, and pose estimation
  • Organizer of PolEval2021 and author of first corpus for punctuation restoration – “PolEval 2021 Task 1: Punctuation restoration from read text”
  • Organizer and team member of AI for Good educational project detect waste in Pomerania
  • Co-organizer of Hack4Environment - hackathon supporting ‘Detect waste’ project
  • ML Lead for detect waste in Pomerania project, published in Waste Management (IF = 6.178)
  • Member of the Board of the Tri-City AI Bay Artificial Intelligence Club
  • Over 1500 citations on Google Scholar as of 2023
  • Member of the Gdańsk University of Technology Faculty Council representing the faculty (2018-2020)
  • Representative of PhD Students at the Faculty Council and Member of the Faculty Scholarship Committee (2018-2020)
  • Organisation of the IAV Cup 2019 competition (member of the Organisational Committee)
  • Organisation of the IAV Cup 2018 competition (member of the Organisational Committee)

Projects

*
All Image Analysis Audio Analysis Explainable AI Data Augmentation Other

Senior AI Engineer at Chaptr.AI

Working with AI assistants, LLMs, LLM-based agents, RAG, and others. Currently working in the book metadata optimization project.

Detecting and Reducing Bias in Data

Currently, in contrast to shallow models exploited in the past, most deep learning systems extract features automatically, and to do …

DetectWaste and ClassifyWaste

The proposed classify-waste benchmark is a merged collection of publicly available datasets with eight classification labels. The …

HearAI

Deaf people are affected by many forms of exclusion, especially now in the pandemic world. HearAI aims to build a deep learning …

Punctuation Restoration

Speech transcripts generated by Automatic Speech Recognition (ASR) systems typically do not contain any punctuation or capitalization. …

Tiny Hero - Generating pixel characters with GANs

Dataset TinyHero includes 64x64 retro-pixel character. All characters were generated with Universal LPC spritesheet by makrohn. Each …

Skin Lesion Classification

In the last twenty years the interest of automated skin lesion classification dynamically increased partially because of public …

Bird Song Classification

Sound-Based Bird Classification using Convolutional Neural Networks and Mel-Cepstrum Sepctrograms

Detect waste in Pomerania

Using detection models to localize and classify waste on images and video.

Hack4Environment

Hackathon. Let's do something for our environment.