Principal Data Scientist- Entity/ID Resolution & Recommender Systems

ZoomInfo is seeking a Principal Data Scientist to join our Innovation Data Science team to develop cutting-edge data products in its industry-leading B2B sales and marketing intelligence platform. If you are a visionary data scientist who thrives on transforming data into high impact customer-facing applications, this is an exciting opportunity to help propel our business to new heights.

About our Team

Our mission is to unlock the full potential of ZI’s extensive B2B data by applying machine learning (ML) and Generative AI to optimize the full Go-to-Market stack. We’ve cultivated a powerful blend of product thinking, modern AI expertise, and iterative methodologies which have delivered a robust suite of data products that inject data-driven intelligence into every facet of ZI. We actively explore existing solutions, adapting them to suit our unique needs while fostering a culture of creativity. Collaboration is at our core, as we work closely with data scientists, product managers, ML engineers, subject-matter experts, and key stakeholders to identify critical gaps and effective solutions to the most valuable problems in our business. The result? An impressive array of both experimental and production-ready AI products that have a tangible impact on our customer’s ability to generate revenue with their Go-to-Market motion. Embrace the opportunity to join our accomplished team on this transformative journey, where innovation and teamwork thrive, and where your contributions will shape the future of data-driven Go-to-Market.

What you'll do:

As part of our Innovation Data Science team, you will play a key role in leading and building out our recommendation, ranking systems, and entity resolution stack, which will support a variety of business use cases:

• Lead the development of state-of-the-art entity and identity resolution algorithms to enhance the accuracy and reliability of our data assets.
• Design and implement advanced recommender systems to identify high-intent companies and contacts, optimizing customer engagement and conversion rates over time.
• Promote a culture of continuous learning and knowledge sharing within the team.
• Identify key signals that drive a user's next best action in order to optimize sales outcomes using advanced probability, statistics, predictive performance, and ML/RL.
• Build innovative new AI solutions, enhance existing models, drive continuous improvement and keep us ahead of industry trends. Promote a culture of continuous learning and knowledge sharing within the team.

• Partner with ML engineers to review and co-optimize technical designs.
• Support the productionization and deployment of data science models and pipelines, ensuring scalability, reliability, and efficiency in real-world applications.
• Spend 30% of your time leading a small team of Data Scientists, providing mentorship, and driving project execution.
• Other duties as assigned

What you will bring:

• Experience: MS + 7yrs or PhD + 5yrs in quantitative field: Statistics, Applied Math, Computer Science, Physics or equivalent. 
• 5+ years of experience building personalized recommender systems and entity resolution algorithms, employing advanced techniques such as deep learning-based models, sequential recommendation algorithms, reinforcement learning frameworks, and/or dynamic re-ranking.
• Proven track record of leading a small team of data scientists, driving project execution, providing mentorship, and fostering a collaborative and innovative team environment. Demonstrated ability to manage multiple projects, prioritize effectively, and deliver high-quality results in a fast-paced setting.
• Skilled in continuous model evaluation and adaptation to evolving user preferences and behavior patterns based on real-world feedback.
• Data-Centric Mindset: Be willing to explore the data and have it guide you to the best solution. Able to utilize a diverse range of advanced statistical and analytic techniques to inform development priorities and decision-making processes.
• Languages and Compute Frameworks: Able to write readable, testable, maintainable and extensible code in Python, SQL, and Spark. Bonus points for Ray.
• Production ML: Experience developing data preparation, model training and inference pipelines using cloud-managed tools like Dataproc, EMR, Airflow, vector databases (FAISS, Pinecone), or equivalent. 
• ML Frameworks: Deep experience w/ PyTorch, XGBoost, SparkML, model registries (Hugging Face), LLM APIs, etc. 
• Theory: Understanding of latest deep learning architectures and when to apply a given pre-trained model. Some experience with techniques like prompt engineering, fine tuning, reinforcement learning w/ human feedback, model distillation and model compression. Up-to-date on recent advances in the LLM space.
• Communication: Able to navigate large projects with multiple collaborators. Excellent cross-functional and verbal communication skills, enabling seamless communication with business partners and stakeholders.

#LI-VC1

#LI-Remote