I’m looking for a developer who can build a robust supervised-learning algorithm end-to-end. I already have a labeled dataset and a clear target variable, so your focus will be on selecting an appropriate model, training it, tuning hyper-parameters, and validating performance. You’re free to work in Python with libraries such as scikit-learn, TensorFlow, or PyTorch—choose the stack that best matches the problem once you see the data. Clean, modular code is key; I want to be able to drop in new data, retrain, and reproduce the results without fuss. Deliverables • Well-documented source code and requirements.txt • A short README explaining setup, training, and inference steps • A concise report summarizing model choice, metrics, and next-step recommendations Acceptance criteria • Minimum accuracy (or relevant metric) agreed upon before training begins • Reproducible results from a fresh environment using the README alone • No hard-coded paths or credentials in the code If this sounds straightforward to you and you have a track record of shipping production-ready supervised models, let’s talk.