About the Role
We are seeking a Data Mining Engineer to join our AI & Analytics team.
You will be responsible ftransforming large-scale IoT sensdata actionable insights predictive models.
Your work will directly support industrial applications such as anomaly detection, predictive maintenance, operational optimization across various domains.
Key Responsibilities
• Design implement data cleaning preprocessing pipelines flarge-scale IoT industrial sensdata.
• Conduct exploratory data analysis (EDA) to uncover patterns, correlations, anomalies.
• Perform feature engineering statistical modeling to extract valuable information from high-frequency time-series data.
• Develop deploy machine learning statistical models fanomaly detection, forecasting, predictive maintenance.
• Build maintain data visualization dashboards analytical reports to communicate findings effectively to business technical stakeholders.
• Collaborate closely with data engineers, domain experts, software developers to ensure end-to-end model integration deployment.
• Continuously evaluate model performance improve algorithms frobustness, scalability, accuracy.
• Contribute to technical documentation, presentations, data-driven reports finternal external stakeholders.
Required Qualifications
• Bachelor’s Master’s degree in Computer Science, Data Science, Applied Mathematics, Statistics, Electrical Engineering, a related field.
• Strong Python programming skills, with experience in scientific data analysis libraries (e.g. pandas, NumPy, scikit-learn, PyTorch, TensorFlow, statsmodels).
• Solid understanding of time-series analysis, signal processing, statistical modeling techniques.
• Experience with data cleaning, missing data handling, outlier detection in noisy IoT environments.
• Familiarity with machine learning algorithms (e.g. clustering, regression, anomaly detection, forecasting models).
• Experience in working with industrial, manufacturing, IoT datasets is a strong plus.
• Proficiency in SQL experience with databases data warehouses (e.g. PostgreSQL, InfluxDB, TimescaleDB).
• Good commof English communication skills — able to document technical work present findings clearly.
• Strong analytical mindset ability to derive insights from complex datasets.
Preferred Qualifications
• Experience with streaming real-time data pipelines (e.g. Kafka, Flink, Spark Streaming).
• Familiarity with cloud platforms such as AWS, Azure, GCP fdata storage model deployment.
• Hands-on experience with Docker / Kubernetes fmodel serving deployment.
• Knowledge of edge AI on-device model optimization fIoT applications.
更多
