Data Scientist

Data Scientist

Requirements

• Master’s degree, or foreign equivalent, in Computer Science, Computer Engineering, or a related field
• One (1) year experience as a Junior Data Scientist, Associate Data Engineer, or related occupation
• Formal version control such as Git
• Extracting, transforming, and loading using structured data sets
• Industry standard data science packages and libraries in Python
• Operating in Agile environment
• Performing data processing and working on analytics initiatives
• Creating data extracts
• Working with Python, NoSQL, and relational databases such as Snowflake
• MYSQL and experience with dashboard / reporting data using BI software such as Tableau and MS Power BI

Responsibilities

• Perform analytical tasks and initiatives on huge amounts of data to support data-driven business decisions and development
• Direct the data gathering, data mining, and data processing processes in huge volume, creating appropriate data models
• Explore, promote, and implement semantic data capabilities through Natural Language Processing, text analysis and machine learning techniques
• Lead to define requirements and scope of data analyses, presenting and reporting possible business insights to management using data visualization technologies
• Conduct research on data model optimization and algorithms to improve effectiveness and accuracy on data analyses
• Develop failure models that help save machine downtime from weeks to months
• Responsible for the development and deployment of predictive analytical models for condition monitoring on Caterpillar engines and machines
• Build based analytical models for active monitoring of mining and construction machinery using high frequency time series (sensory) data using Python
• Develop Python packages and machine learning models for Caterpillar partners maintaining data privacy using AWS workspaces and Sage maker
• Develop end to end strategy starting from data modelling to communicating insights to SME’s and business partners
• Develop back-testing strategies and validating models to compute model performance metrics
• Develop Python packages and rule-based algorithms to solve efficient problems faced during data retrieval and model development
• Work on SQL using Snowflake and SQL Alchemy to have a data pipeline ready for condition monitoring and statistical metrics
• Lead Failure Modelling deployment pipeline for all industry partner requests
• Develop dashboards using Power BI to identify patterns on model triggers
• Responsible for presenting insights to business and cross industry partners on on-prem tools and projects

Preferred Qualifications

No preferred qualifications provided.