Machine Learning Engineer II - Recommendations (REMOTE) at DICK'S Sporting Goods

At DICK’S Sporting Goods, we believe in how positively sports can change lives. On our team, everyone plays a critical role in creating confidence and excitement by personally equipping all athletes to achieve their dreams.  We are committed to creating an inclusive and diverse workforce, reflecting the communities we serve.

If you are ready to make a difference as part of the world’s greatest sports team, apply to join our team today!

OVERVIEW:

At DICK’S Sporting Goods, we believe sports can change lives. Founded in 1948, DICK’S Sporting Goods first started as a bait-and-tackle shop in Binghamton, NY and has since rapidly expanded into a leading omnichannel retailer with more than 850 locations representing our multiple brands: DICK’S, House of Sport, Golf Galaxy, Public Lands, Going Going Gone, and more. Over the years, it’s been our relentless focus on inspiring, supporting and equipping athletes and outdoor enthusiasts to achieve their dreams that has allowed us to become the $13B company we are today.

Our company is looking to invest in our future as we embark on a journey from being the best sports retailer in the world to becoming the best sports company in the world. We aim to build the ultimate athlete data set that will power our tools and platforms for the most personalized athlete experiences. Join us as we transform our technology, data and analytics to build next-gen tools and platforms for our athletes and teammates. If you are ready to make a difference as part of the world’s greatest sports company, apply today!

JOB RESPONSIBILITIES:

Designs machine learning systems to create artificial intelligence applications and products. Researches and implements algorithms and platforms, train/retrain systems, conduct learning tests and experiments, and develop applications according to requirements. Extends existing machine learning libraries and frameworks.

• Data Set Exploration and Documentation: Analyze, document and speak to complex datasets while establishing quality and the lineage of the data. Establish different techniques of feature engineering and of scalable feature store technology. Employ relevant data embedding techniques to codify different kinds of data signals relevant for machine learning models

• Software Development: Develop existing software and contribute to development of new software by analyzing and identifying areas for modification and improvement. Develop new software that is fast, secure and reliable to meet defined requirements. Employ best practices of Machine Learning Operations to build scalable ML software. Write production quality code for ML as services and APIs. Be involved in all parts of the Machine Learning lifecycle: data exploration, modeling, evaluation, deployment and monitoring. 

• Technical Developments Recommendation: Research and suggest ways to optimize solutions to better meet user and/or business, performance, quality needs, specifically in the areas of deep learning and recommender systems

• Analysis of Current vs. Future State: Document Current vs Future state processes and describe the changes required to migrate to the future-state capability to record accurately the change required.

• Data Architecture: Understands the basics of modeling and is able to implement best practices for data architecture. Selects the appropriate technology for the implementation of solutions. Understands in theory & practice end to end ML architecture and the latest technologies that build for scale and efficient deployments

• Quality: Plan and coordinate testing and inspection of products and processes. . Help management to implement quality assurance change initiatives and/or make continuous operational improvements.

• Program/Portfolio Management Support: Understand how to work within an established program management plan to achieve specific goals.

• Information Security and Compliance: Readily identifies sensitive data and applies best practices associated with its classification and handling

• Ongoing Learning and Development: Develop own capabilities by participating in assessment and development planning activities as well as formal and informal training and coaching; gain or maintain external professional accreditation where relevant to improve performance and fulfill personal potential. Maintain an understanding of relevant technology, external regulation, and industry best practices through ongoing education, attending conferences, and reading specialist media.

QUALIFICATIONS:

• Bachelor's Degree or equivalent level preferred in quantitative fields like computer science, engineering, physics, math, etc.

• Substantial general work experience together with comprehensive job related experience in own area of expertise to fully competent level (Over 13months to 3 years )

TECH STACK:

• Understanding of build infrastructure and CI/CD related technologies such as Docker, Bash scripting, Jenkins, compilers, linkers, CMake etc.

• Proficient knowledge on MLOps: Real-time serving, Spark expertise (PySpark, Scala), workflow orchestration, end-to-end solutioning, operational monitoring, model monitoring, model registry, feature store, advanced feature engineering (Deep Learning, vector DBs)

• Proficient knowledge in standard and advanced machine learning algorithms, their complexity and implementation procedures.

• Experience deploying machine learning models within the recommender systems & customer personalization space (1+ years)