Data Scientist

Join Hadrian, a cutting-edge aerospace manufacturing company, as a Data Scientist. In this role, you will focus on modeling and predicting manufacturing processes, utilizing rich process data generated by our factories. You will work on forecasting and prediction, representation learning, and geometric modeling, while building and shipping production models for cycle time, tool life, quality, and demand. You will also own the end-to-end model lifecycle, from training to serving and monitoring, and turn predictions into actionable decisions for quoting, scheduling, capacity, and DFM.

• Predire le performance del processo di produzione prima che inizi, migliorando continuamente le previsioni con ogni parte prodotta.
• Sviluppare e implementare modelli di apprendimento automatico per prevedere il tempo di ciclo, la vita degli utensili, la qualità e la domanda, utilizzando incertezze calibrate.
• Collaborare con il team di piattaforma ML e ingegneria dei dati per implementare e monitorare i modelli in produzione, garantendo la loro efficacia nel tempo.

• Forecasting and prediction on real, messy manufacturing data, with honest uncertainty
• Deploys and monitors models; thinks about pipelines and drift from the start, not after
• Representation learning and embeddings; similarity and retrieval; transfer/few-shot for sparse data
• Strong classical ML and statistics (GBMs, Bayesian/hierarchical, survival, causal)
• Works with limited, high-value data and knows how to borrow strength
• Python; turns a messy process into features and a model into a decision an operator or a downstream system can consume
• Deep learning that ships (PyTorch), and the judgment to know when not to use it
• Validation done right: backtesting, leakage control (time and part-family), calibration
• Geometric deep learning: mesh / point-cloud networks, GNNs, PyTorch Geometric
• CAD / B-rep, feature recognition, and turning part geometry into ML features
• Retrieval and ANN at scale; embedding stores
• Bayesian and hierarchical modeling for small data; physics-informed ML
• Survival and reliability modeling (tool life, degradation)
• Aerospace or precision-manufacturing background; DFM intuition
• Digital twins and simulation; causal inference; sensor / IoT data