Lead Machine Learning Engineer, Shopping – Feed
Are you applying to the internship?
Job Description
About the Company:
Capital One is seeking professionals for a Lead Machine Learning Engineer position within their Capital One Shopping division. They are a growth-stage line of business operating with a startup mindset, focused on building technology to save customers money. The company emphasizes a dynamic, remote-first engineering team and a fast-paced, collaborative environment. They are committed to diversity and inclusion and offer a comprehensive benefits package.
Job Description: Lead Machine Learning Engineer, Shopping – Feed (Remote)
This is a remote position offering a chance to be part of a fast-moving, highly collaborative Agile team. The role involves productionizing machine learning applications and systems at scale. As a Lead Machine Learning Engineer (MLE), responsibilities include:
• Leading Machine Learning Architectural Design: Driving the detailed technical designs, development, and implementation of machine learning applications using existing and emerging technology platforms. This includes being a key decision-maker in the architecture and design process.
• Model Development and Review: Developing and reviewing model and application code, ensuring high availability and performance of ML applications. This involves actively participating in code reviews and ensuring high quality of the codebase.
• Next-Generation Model Research: Contributing to researching the next generation of models and recommendation systems to deliver improved value to customers. This requires a proactive approach to researching new algorithms and techniques to improve the existing system.
• Mentorship and Collaboration: Mentoring junior developers and serving as a technical bridge between product partners. This includes providing guidance and support to junior team members and facilitating effective communication between engineering and product teams.
• Technical Proficiency: Using tools such as Docker, Nomad, SQL, Python, PyTorch, Transformers, language models, and other statistical tools. Proficiency in these tools is essential for success in this role.
The MLE role is multifaceted, overlapping with Operations, Modeling, and Data Engineering. Key responsibilities include:
• Model Building and Delivery: Designing, building, and delivering ML models and components to solve real-world business problems, collaborating with Product and Data Science teams.
• Infrastructure Decisions: Informing ML infrastructure choices based on an understanding of ML modeling techniques and issues (model selection, data/feature selection, training, hyperparameter tuning, dimensionality reduction, bias/variance tradeoff, and validation).
• Problem Solving and Code Development: Solving complex problems by writing and testing application code, developing and validating ML models, and automating tests and deployment.
• Team Collaboration: Collaborating within a cross-functional Agile team to create and enhance software for big data and ML applications.
• Model Maintenance and Monitoring: Retraining, maintaining, and monitoring models in production to ensure optimal performance and accuracy.
• Cloud-Based Architectures: Leveraging or building cloud-based architectures, technologies, and/or platforms for optimized ML model delivery at scale.
• Data Pipeline Construction: Constructing optimized data pipelines to feed ML models efficiently.
• CI/CD Best Practices: Leveraging CI/CD best practices, including test automation and monitoring, for successful deployment.
• Code Management and Responsible AI: Ensuring well-managed code to reduce vulnerabilities, well-governed models from a risk perspective, and adherence to Responsible and Explainable AI best practices.
• Programming Languages: Using programming languages such as Python, Scala, or Java.
• Model Research and Design: Designing and researching new models using data scientist experience/expertise.
The position requires a Bachelor’s degree and significant experience in designing data-intensive solutions, programming in Python/Scala/Java, and building/scaling/optimizing ML systems. Preferred qualifications include a Master’s or Doctoral degree and experience with specific ML frameworks and data pipelines.
