Senior Data Scientist - IDS2002

Key Skills

AWS, Azure, C++, Cyber Security, Data science techniques, Google Cloud Platform (GCP), Java Programming, Keras software library, Machine learning techniques, Pandas, Python Programming, R Programming, Scikit-learn, SPARK Programming, SQL, TensorFlow

Job Description

Mastercard is a global technology company in the payments sector. We power payments and provide products and services for individuals and industries all around the world. Our people, technology, data, and brand provide the capabilities that drive our success. We believe in connecting people to priceless possibilities.

As a company, we know that our success is driven by the skills, experience, integrity and mindset of the talent we hire. By building an inclusive, world-class culture, our employees have once-in-a-career opportunities to be a part of teams that have a greater impact on our community and our world. We invite you to join our team to find out how you too can start something priceless. 

Overview

Mastercard's Cyber & Intelligence organization develops and delivers world-class security products and services for customers across the globe. NuData Security predicts fraudulent transactions by identifying good users from bad, based on their online behaviour. By analyzing over 38 billion behaviours annually, NuData harnesses the power of behavioral and biometric analysis to empower its clients to predict fraud and verify the user behind the device. This allows clients to predict fraud before a critical decision, reduce customer insult, and investigate bad actors efficiently.

Role

• We are looking for a Data Scientist with a minimum of 3 years of experience in a related field to join our team in the Vancouver office. This is a key role within the team responsible for developing models to support various NuData products, and you’ll have exciting responsibilities, including:
• Analyzing complex, high-volume data from varying sources and identifying key regularities, patterns and trends.
• Prototyping and developing machine learning models in collaboration with an agile, high-functioning team.
• Spotting new opportunities in data collection, feature creation, feature selection, model tuning and evaluation practices, and taking those ideas from the first concepts to live product integrations.
• Implementing effective monitoring and benchmarking for model performance comparison.
• Leveraging new research in data modeling to identify opportunities, pioneering algorithms and systems that become key commercial products.
• Maintaining model development pipelines, libraries and machine learning infrastructure.

All About You

Ideally, you are:

• A strong problem solver with critical thinking skills who can formulate a problem into a solution.
• Capable of writing complex SQL queries to process data. Proficient with manipulating and analyzing data to gain meaningful insights using tools such as Pandas for Python.
• Experienced in creating algorithms and applying machine learning models to solve real business problems. You have the vision to see what the next-generation model looks like and can iterate over production models to generate a competitive edge in the market.
• A capable coder, able to write well-abstracted, production-quality code in Python (preferred), R, Java and/or C++. You’re experienced in using cloud services (e.g. AWS, Microsoft Azure and/or Google Cloud), and machine learning tools (e.g. sci-kit-learn, Tensorflow and/or Keras).
• Statistically adept. You have the depth of knowledge required to identify appropriate techniques, follow and create formal proofs, define apt performance measures and adeptly explore or transform data. Ideally, you have studied in a quantitative field at a doctoral or master’s level.
• Experienced working with large data sets. You understand the benefits of batch processing and parallelization and know how to design a pipeline to scale out machine learning workflows. You have experience working with distributed data processing frameworks such as Apache Spark.
• An effective communicator in visual, verbal and spoken channels, able to identify a narrative in complex data and convey clear, actionable findings to different types of audiences.
• Experienced in architecting end-to-end solutions for production deployment (considered an asset but not required).

It also helps if you are:

• Collaborative. We do our best work as a team, which means sharing, and being open to giving and receiving support and constructive input.
• Evidence-based. We work to eliminate assumptions and test our hypotheses, and we value rigor.

• Responsible. We offer the opportunity to drive major projects that protect consumers every day, internationally. We are looking for colleagues who care about that.
• Motivated. We’re a team of data scientists with personal and collaborative side projects, and we’re looking for someone who shares our enthusiasm.
• Innovative. Data Science is a continuously growing field. We like our team to keep pushing for new ideas and methods. We are looking for someone who is creative and not just always satisfied with the status quo.