Skip to content
View Pawcharz's full-sized avatar

Organizations

@Gradient-PG @TheLion-ai

Block or report Pawcharz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pawcharz/README.md

Hi there 👋

  • I'm an ML Engineer building intelligent systems and doing research in machine learning.
  • My interests span mechanistic interpretability, reinforcement learning, and multimodal AI.
  • I work as an ML Engineer at TeaCode.io, building production AI systems.
  • I recently completed my B.Eng. in Data Engineering (thesis graded 5/5, graduated early 2026).

🔭 I'm currently working on

  • Mechanistic Interpretability Paper → Co-authoring a paper with Miłosz Grunwald on discriminative neurons in BERT for AI-generated text detection, using causal ablation and activation patching. Targeting A* tier conferences.
  • RL Explainability Research → Member of the Off-the-Grid project at Gradient PG, exploring whether strategies learned by DRL agents can be extracted into human-readable symbolic rules.

⚡ Skills

  • Programming: Python (PyTorch, TensorFlow, Keras), JavaScript/TypeScript (React, React Native, Node.js), C# (.NET/Unity), C/C++
  • AI/ML: Deep Learning, Mechanistic Interpretability, Natural Language Processing, Reinforcement Learning, Computer Vision, LLMs
  • Other: Data pipelines, web & mobile development, full-stack AI apps, EDA

📫 How to contact me

If you're looking for a collaborator on a research topic or applied ML project, feel free to reach out.

Pinned Loading

  1. autoresearcher autoresearcher Public

    Autonomous researcher working overnight on your ML codebase. Define directions, run Claude Code, wake up to findings. It explores the code, runs experiments, analyzes papers and iterates on new res…

    Python 1

  2. warehouse-bot-training warehouse-bot-training Public

    Custom PPO implementation with multimodal observations (CNN + task embeddings) for training a warehouse navigation agent in Unity

    Python

  3. warehouse-bot warehouse-bot Public

    Simulation of agent moving objects to a given location in a simulated environment using deep learning techniques.

    C#

  4. knee-osteoarthritis knee-osteoarthritis Public

    Classification of knee osteoarthritis based on X-Ray images with use of deep neural networks. (Built with PyTorch, Torchvision, OpenCv, Optuna framework).

    Jupyter Notebook