<hello/> _

Agnieszka
Mikołajczyk-Bareła

PhD · Senior AI Engineer · Researcher

Senior AI Engineer building Reedy at Chaptr.AI — LLMs, RAG, and multimodal pipelines. Formerly led the NLP team at VoiceLab.AI that shipped TRURL, Poland's first large-scale generative model. Researcher, speaker, and mentor with a track record of leading AI-for-Good initiatives.

3 200+ citations across 30+ papers and 10+ open-source projects. Named among Top Women in AI Poland.

Skills

LLMs & AI Agents — LLM Training · Fine-tuning · RAG · LangChain · Agentic Pipelines · Prompt Engineering · Evaluation · Pydantic · OpenAI / Claude / Gemini / Llama

NLP & Speech — Transformers · BERT · GPT · TTS · ASR · Sentiment Analysis · NER

Computer Vision & Multimodal — EfficientDet · DETR · Mask R-CNN · GANs · Vision Transformers · Image Generation · Video Generation

Explainable AI — Attention Maps · Counterfactual Analysis · Bias Detection · Global Explanations

Data & Annotation — Dataset Curation · Annotation Pipelines · Data Cleaning · Benchmarking · Crowdsourcing

ML Engineering — Python · PyTorch · HuggingFace · ONNX · Model Training & Deployment

Projects

Research, open-source, and industry work

featured

Reedy — AI Metadata Platform for Publishers

LLM RAG NLP Multimodal

Building Reedy at Chaptr.AI — an AI engine that generates keywords, THEMA codes, and SEO descriptions for book catalogs. RAG pipelines, trend analysis, and multimodal AI across TTS, ASR, and image/video generation.

Reedy → Chaptr →

featured

HearAI — Sign Language Recognition

Deep Learning AI4Good

Making the world more accessible for the Deaf community through deep learning-based sign language recognition.

Website → Code →

featured

Detect Waste in Pomerania

Computer Vision AI4Good Deep Learning

WiMLDS Trójmiasto AI4Good project training custom PyTorch detection & segmentation models (EfficientDet, DETR, Mask R-CNN, Faster R-CNN) to localize waste in the environment. Published in Waste Management (IF 6.1). 220+ GitHub stars.

GitHub ★220 → Paper → Website →

featured

GEBI — Global Explanations for Bias Identification

XAI Research Grant Deep Learning

PhD research (NCN Preludium 18, 138k PLN). Built GEBI — attention-based framework for detecting bias in data using global explanations, counterfactual bias insertion, and spectral clustering. Validated on skin lesion datasets.

Code → Paper →

featured

Data Augmentation Review

Deep Learning Datasets Open Source

Curated collection of data augmentation resources — techniques, libraries, papers, and code. One of the most popular ML repos on GitHub with 1.6k+ stars.

GitHub ★1.6k →

Skin Lesion Classification & GAN Debiasing

Deep Learning Medicine GANs XAI

Trained CNNs, EfficientNets, and StyleGAN2-ADA for skin cancer detection and bias analysis. MICCAI 2022 paper studied how GAN-generated data amplifies or reduces biases in medical imaging.

Code → Paper →