Senior Data Scientist

Senior Data Scientist (Ref.No. R1013045)

at our location in Singapore

Hitachi Rail is looking for an enthusiastic self-motivated skilled Senior Data Scientist with proven experience in data science and software development with strong leadership capabilities. This role combines advanced technical expertise with the ability to manage and supervise junior engineer for ensuring quality, compliance, and timely delivery, and also growth of the team. The ideal candidate shall be confident collaborating with cross-functional teams to implement robust and scalable solutions that drive our HMAX development initiatives.

The position is based in Singapore.

You will enjoy having these responsibilities:

• Responsible for defining the data science and advanced analytics requirements and use cases, creating data exploitation models, recommending tool selection and working closely with HMAX solution core team to create insight and value from data
• Responsible for planning, executing and delivering advanced data analytics and scenario modelling,
• Leading the activities for use case capture, building models, problem analysis, data exploration and data collection and integration,
• Researching existing product and machine learning/deep learning model, proposing improvement and industrializing the product,
• Participating in model demonstration and validation with end customer, providing analysis and evidence of the model performance to demonstrate that the model is fit for production and operation,
• Working with the product leader, domain expert and the software development team to ensure the success of the delivery.

You have:

• Bachelor, Master Degree or PhD in Data Science or related field,
• Minimum 5 years of experience working in artificial intelligence algorithms and a proven record of accomplishment in the implementation of Machine Learning and Deep learning solution based,

• Core Data Science & Machine Learning Skills
• Strong foundation in statistics, machine learning, and data analysis.
• Experience building and deploying predictive models, including classification, regression, clustering, and anomaly detection.
• Familiarity with time-series analysis and forecasting techniques (ARIMA, Prophet, LSTM, temporal CNNs)
• Hands-on experience developing predictive maintenance models is an advantage, including:
• Remaining Useful Life (RUL) prediction
• Failure prediction and classification
• Anomaly detection (e.g., isolation forest, autoencoders)
• Experience with model evaluation, validation, and performance monitoring in production environments.

• Domain Knowledge – Asset & Maintenance Analytics
• Good understanding of industrial asset management concepts, including:
• Reliability engineering (MTBF, MTTR, failure modes)
• Preventive, predictive, and condition-based maintenance strategies is advantage.

• Familiarity with sensor data (IoT / telemetry) such as vibration, temperature, pressure is advantage
• Experience working with industrial standards and frameworks (e.g., ISO 55000, reliability-centered maintenance) is a plus.
• Ability to translate business/engineering problems into data science solutions.

• Data Engineering, MLOps
• Strong proficiency in Python (Pandas, NumPy, Scikit-learn, PyTorch/TensorFlow).
• Experience handling large-scale time-series and streaming data.
• Experience working in cloud environments
• Understanding of MLOps practices
• Experience deploying models as APIs or microservices.
• Proficiency in Italian would be an advantage for communication with Italian-speaking stakeholders.