I’m expanding our team with an AI engineer who can take the lead on end-to-end Machine Learning work. The immediate focus is on time-series data: everything from cleaning raw feeds through to building and shipping a production-ready predictive model. You’ll be working in Python (think pandas, NumPy, scikit-learn, TensorFlow or PyTorch) and will have the freedom to introduce the tools you’re most comfortable with, as long as the final stack is reproducible and easy to maintain. Here’s what I need from you: • Prepare and engineer the time-series dataset so that it’s model-ready, documenting every transformation. • Design, train, and iterate on forecasting or anomaly-detection models that outperform a naive baseline. • Hand over clean, well-commented code—preferably in a notebook plus modular scripts—together with a brief report on feature importance and performance metrics (MAE, RMSE, or other relevant scores). • Package the solution for deployment, for example through a RESTful FastAPI service or a Docker image, and include a one-click setup guide. Strong API familiarity is essential because this model will later plug into a larger automation pipeline. If you have prior experience operationalising LLMs, that’s a welcome bonus, but the core of this role is classic ML craftsmanship. Sound like a good fit? Send a short note describing a recent time-series project, your preferred libraries, and your typical turnaround time, and we can dive into the details.