Skip to content
View designer-coderajay's full-sized avatar

Block or report designer-coderajay

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
designer-coderajay/README.md

Typing SVG


🎓 MSc AI @ Hochschule Trier | 📍 Germany

🔬 Research Focus

Mechanistic interpretability: activation patching, logit lens, induction heads, superposition. Currently writing my thesis on explainable AI for LLMs with causally grounded natural language explanations.

🏅 Certifications

Professional Exams

Azure Azure

Specialized Training

Safety Azure Hugging Face

🛠️ Tech Stack

AI/ML: PyTorch, TransformerLens, Hugging Face, LangChain Cloud: Azure OpenAI, Azure ML, Azure Cognitive Services LLM: GPT-4, Claude, Llama, Fine-tuning, RAG, Agents MLOps: MLflow, DVC, Docker, FastAPI, GitHub Actions

📊 Current Focus

  • 🔬 MSc Thesis: Mechanistic Interpretability of LLMs
  • 🚀 Building production LLM applications
  • 🎯 Seeking AI/ML Engineer roles in EU

📫 Connect

LinkedIn Email

Pinned Loading

  1. XAI-for-LLMs-Causally-Grounded-Mechanistic-Interpretability-Concise-Natural-Language-Explanations XAI-for-LLMs-Causally-Grounded-Mechanistic-Interpretability-Concise-Natural-Language-Explanations Public

    MSc Thesis: Bridging mechanistic interpretability circuits to faithful natural language explanations using ERASER evaluation metrics

    Jupyter Notebook 1

  2. glassbox glassbox Public

    See inside AI models in 3 lines of code. Simple mechanistic interpretability toolkit.

    Python 1

  3. azure-ai-rag-system azure-ai-rag-system Public

    Production RAG system using Azure OpenAI + Azure AI Search + Blob Storage. Hybrid vector search, document chunking, streaming responses.

    Python 1

  4. azure-ml-pipeline azure-ml-pipeline Public

    End-to-end ML pipeline on Azure Machine Learning for heart disease prediction. Features 4-step automated workflow (data prep, training, evaluation, registration), MLflow experiment tracking, and ma…

    Python 1

  5. activation-patching-framework activation-patching-framework Public

    Causal intervention framework for mechanistic interpretability research. Implements activation patching methodology for identifying causally important components in transformer language models.

    Python 1

  6. logit-lens-explorer logit-lens-explorer Public

    Mechanistic interpretability tool visualizing GPT-2's layer-by-layer predictions using the logit lens technique

    Python 2