Wayne SimmonsOpen to 2027 ML internships
Resume

[01] Work

The pipeline

Everything I've built or am building, newest first. Each one opens into a model card: the task, the data, the model, and what actually happened.

4 done1 in progress1 next

All projects with task, stack, status, and year
#ProjectTaskStackStatusYear
01Autonomous Data Analyst AgentAn agent that takes a plain-English business question, writes SQL against a real database, runs Python analysis in a sandbox, makes charts, and writes up what it found.Answer business questions end to end, autonomouslyPython, MCP, Postgres, FastAPI, Docker, Langfuse[next]2026
02Claude RAG ChatbotA Streamlit chatbot on the Claude API that routes each question to the right knowledge base and answers grounded in it.Retrieval-augmented question answeringPython, Streamlit, Anthropic API[done]2026
03CUAD Contract TriageA pipeline that finds the risky clauses in commercial contracts and ranks which contracts a legal team should open first. Built for Accenture with a 7-person Break Through Tech AI Studio team.Multi-label clause detection + risk triagePython, scikit-learn, Hugging Face Transformers, PyTorch, pandas[in progress]2026
04What 114,000 Songs Sound LikeAn honest look at Spotify's catalog as data, ending in an interactive explorer you can filter yourself.Exploratory analysis + interactive explorerPython, pandas, Plotly, Streamlit[done]2026
05Decision Tree vs Neural NetworkTwo models on the Titanic dataset, taken through the full ML life cycle side by side, then scored against Kaggle's real holdout.Binary classification (passenger survival)Python, scikit-learn, Keras, pandas, Streamlit[done]2026
06CleanTubeA search-only front door to YouTube. No home feed, no recommendations. Arrive with intent, find it, leave.Cut algorithmic noise out of YouTubeHTML, JavaScript, Claude[done]2026