Full-Time Machine Learning Engineer

• Lead technical delivery: Drive the development of pipelines for transforming raw sensor data using time-windowing, FFT, and domain-specific features.
• Shape architecture: Design and implement anomaly and failure detection models, both unsupervised (Isolation Forest, One-Class SVM) and supervised (XGBoost, Random Forest).
• Collaborate across roles: Bridge data science, engineering, and domain teams to align on requirements and delivery plans. Support RUL forecasting with time-series models like LSTM.
• Ensure delivery excellence: Apply explainable AI tools (LIME, SHAP) and create diagnostic visualizations to build trust and transparency. Maintain strong experiment tracking, versioning, and deployment using MLflow for reliable production workflows
• Mentor and support: Guide the team through the ML lifecycle, secure deployments, and monitoring. Provide mentorship, support onboarding, and encourage technical growth and consistency

• 4+ years of experience with Python and its data science ecosystem (Pandas, NumPy, Scikit-learn).
• Proficiency in advanced feature engineering techniques, including the transformation of raw sensor data into meaningful features for machine learning models.
• Hands-on experience with unsupervised anomaly detection algorithms, such as Isolation Forest and One-Class SVM.
• Solid expertise in supervised machine learning models, including Random Forest and XGBoost for fault classification, along with practical experience in time-series networks (e.g., LSTM) for Remaining Useful Life (RUL) prediction.
• Good understanding of explainable AI frameworks, such as LIME and SHAP.
• Experience with MLOps practices and tools, including MLflow or similar frameworks.

What is the last date for applying to the job?

Which countries are accepted for this remote job?