Senior ML Scientist (EDA and building and training ML models)

Company Description

Visa is a world leader in payments and technology, with over 259 billion payments transactions flowing safely between consumers, merchants, financial institutions, and government entities in more than 200 countries and territories each year. Our mission is to connect the world through the most innovative, convenient, reliable, and secure payments network, enabling individuals, businesses, and economies to thrive while driven by a common purpose – to uplift everyone, everywhere by being the best way to pay and be paid.

Make an impact with a purpose-driven industry leader. Join us today and experience Life at Visa.

Job Description

Team Summary:

The Risk and Identity Solutions (RaIS) team provides risk management services for banks, merchants, and other payment networks. Machine learning and AI models are the heart of the real-time insights used by our clients to manage risk. Created by the Visa Predictive Models (VPM) team, continual improvement and efficient deployment of these models is essential for our future success. To support our rapidly growing suite of predictive models we are looking for engineers who are passionate about managing large volumes of data, creating efficient, automated processes and standardizing ML/AI tools.

Job Description

This is a great opportunity to work with a new Data Engineering and MLOps team to scale and structure large scale data engineering and ML/AI that drives significant revenue for Visa. As a member of the Risk and Identify Solutions modeling organization (VPM), your role will involve developing and implementing practices that will allow deployment of machine learning models in large data science projects.

You must be a hands-on expert able to navigate both data engineering and data science disciplines to build effective engineering solutions that support ML/AI models. You will partner closely with global stakeholders in RaIS Product, VPM Data Science and Visa Research to help create and prioritize our strategic roadmap.  You will then leverage your expert technical knowledge of data engineering, tools and data architecture in the design and creation of the solutions on our roadmap.

The position is based at Visa's offices in Bangalore, India.

Essential Functions:

• Proficient in exploratory data analysis (EDA) using Python's scientific libraries including numpy, pandas, matplotlib, seaborn, and scikit-learn
• Exposure to model development frameworks like MLFlow
• Experience using Papermill for parameterizing and executing Jupyter Notebooks
• Strong development experience in at least one of the following: Python, R (preferably Python)
• Implementation of MLOps practices including continuous integration and deployment (CI/CD) for ML models
• Hands on experience in building and maintaining data pipelines, feature engineering pipelines and comfortable with core ML concepts.
• Hands-on experience in engineering, testing, validating, and productizing ML models for high-performance use cases
• Hands-on experience with AWS Sagemaker for building, training, and deploying ML models
• Develop and implement practices for deploying machine learning models in large data science projects
• Proven experience in building and training complex ML models
• Experience using and maintaining DevOps tools and implementing automations for production
• Additional knowledge of AWS services and ecosystems
• Experience working with containerized and virtualized environments (Docker, K8s)

This is a hybrid position. Expectation of days in office will be confirmed by your hiring manager.

Qualifications

Basic Qualification

• 4+ yrs. work experience with a Bachelor’s Degree or 2+ years of work experience with a Master's or Advanced Degree in an analytical field such as computer science, statistics, finance, economics or relevant area.

Technical skills:

• Proficient in Exploratory data analysis (EDA) using Python's scientific libraries including numpy, pandas, matplotlib, seaborn, and scikit-learn
• Exposure to frameworks like ML flow for model lifecycle management
• Proven experience in building and training complex ML models.
• Strong development experience in programming languages, preferably Python
• Experience with complex, high-volume, multi-dimensional data, as well as machine learning models based on unstructured, structured, and streaming datasets.
• Experience with Unix/Shell or Python scripting and exposure to scheduling tools like Oozie and Airflow.
• Experience with SQL for extracting, aggregating, and processing big data pipelines using Hadoop, EMR, and NoSQL Databases.
• Experience using Papermill for parameterizing and executing Jupyter Notebooks.

Preferred Qualification

• Exposure to model serving engines such as Tensorflow, Triton etc.
• Spark Pipelines: Build and maintain efficient and robust Spark pipelines to create and access data sets and feature stores for ML models.
• ETL processes: The role also involves developing and executing large scale
• ETL processes to support data quality, reporting, data marts, and predictive modeling.
• Hands-on experience with AWS SageMaker for building, training, and deploying ML models.
• Knowledge of standard Big data and Real Time stack such as Hadoop, Spark, Kafka, Redis, Flink and similar technologies
• Implementation of MLOps practices, including continuous integration and deployment (CI/CD) for ML models.

Additional Information

Visa is an EEO Employer. Qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, sexual orientation, gender identity, disability or protected veteran status. Visa will also consider for employment qualified applicants with criminal histories in a manner consistent with EEOC guidelines and applicable local law.