Role Summary/Purpose
As a Business Intelligence (BI) Developer, you will be a dynamic and highly motivated individual with extensive experience working with internal stakeholders in acquiring and refining business requirements for business intelligence solutions in the financial industry. You will design, develop, and implement Natural Language Processing (NLP) solutions that will lead to increased efficiency and profitability across Operations. You will work in the Apache Spark framework and its machine learning library (Spark ML) to build scalable NLP pipelines using Python and PySpark.
Essential Responsibilities
- As a Business Intelligence Developer, you will identify insights and opportunities for increased efficiency and growth across functions in operations.
- You will build and analyze metrics that can be leveraged for business performance measurement, management, QA enhancement and improvement and derive insights about behavior of customers and agents
- Provide advanced analytics and experimentation support, enabling data-driven solutions by applying statistical techniques to solve business problems
- Demonstrate subject matter expertise and technical leadership in data extraction and manipulation, dash-boarding, visualization, and analytical/statistical/data mining techniques
- Deliver user-friendly and informative dashboards and recurring reports, iterating and prototyping to meet business needs
- Responsible for creating, optimizing and automating Spark NLP pipelines to process large volumes of text data efficiently
- Extract relevant features from text data to improve the performance of NLP models
- Assess the accuracy of NLP models and identifying areas for improvement through metrics like precision, recall, and F1-score
- Connecting Spark NLP pipelines with other data processing systems and applications, including data warehouses, databases, and visualization tools.
- Identify new innovative opportunities to drive performance improvement, efficiency, and cost savings
Required Skills/Knowledge
- Bachelor’s degree (or foreign equivalent) in any discipline and minimum 5+ years of Business Intelligence experience within financial services, banking, or retail finance, or in lieu of degree, 7+ years' Machine Learning experience within financial services, banking, or retail finance
- Minimum of 3+ years of experience in Natural Language Processing
- Minimum 2+ years of Tableau, Power BI or other data visualization tool
Desired Characteristics
- Strong background in ETL pipeline development in Anaconda Enterprise and proficiency in Python and SQL
- Experience working with Apache Spark framework and machine learning library (Spark ML) to build scalable NLP pipelines
- Extensive Python/PySpark ETL pipeline development experience
- Strong data visualization experience with Tableau utilizing data visualization best practices and performance optimization
- Effective communication skills with stakeholders, business analysts, architects and other developers