Job Description

DATA SCIENTIST RESPONSIBILITIES

Role expectation:

Model Retraining: Regularly retrain machine learning models to ensure optimal performance, taking into account new data, changes in patterns, or shifts in user behavior. This involves validating, selecting, and fine-tuning the most appropriate models based on the latest available data and adjusting hyperparameters as needed.

Issue Identification: Analyse and interpret model outputs to identify the nature of issues. This may involve anomaly detection, root cause analysis, or pattern recognition to ensure quick resolution and minimize disruption.

Data Pipeline: Investigate and work with his team to resolve any issues related to the data pipeline.

Reporting and Documentation: Keep documentation of model development, retraining, and performance evaluation. Communicate findings, insights, and recommendations to stakeholders and team members in a clear and concise manner.

Skills:

• Knowledge, Skills, and/or Abilities Required: Hands on programming/scripting experience in Java and Python
• Confident statistical and machine learning skills
• Model forecasting and training on DataBricks with Apache Spark
• Strong experience with practical data science and hands-on involvement with deployed ML pipelines in a business environment
• Relevant SQL skills, Azure Data Lake
• Experience building and maintaining data lakes: including ETL skills in Talend /Informatica or related middleware
• Team player with great communication skills and willing to help the other team members.
• Proactive and self-motivated
• Min 2 years experience working as a Data Scientist or BI Intelligence
• Fluency in English is required.