Staff Applied Scientist, Deep Learning Forecasting

The Trade Desk is a global technology company with a mission to create a better, more open internet for everyone through principled, intelligent advertising. Handling over 1 trillion queries per day, our platform operates at an unprecedented scale. We have also built something even stronger and more valuable: an award-winning culture based on trust, ownership, empathy, and collaboration. We value the unique experiences and perspectives that each person brings to The Trade Desk, and we are committed to fostering inclusive spaces where everyone can bring their authentic selves to work every day.

Do you have a passion for solving hard problems at scale? Are you eager to join a dynamic, globally connected team where your contributions will make a meaningful difference in building a better media ecosystem? Come and see why Fortune magazine consistently ranks The Trade Desk among the best small-medium-sized workplaces globally.

ABOUT THE ROLE

Applied Scientists  at TTD work closely with engineering throughout the lifecycle of the product, from ideation to productionalization and monitoring. Our data scientists are end-to-end owners. You will participate actively in all aspects of designing, researching, building, and delivering data-focused products for our clients and traders.

This role is responsible for the research and application of forecasting models to support planning and recommendation related products across the platform. Accurate forecasting is critical for us to give timely feedback on user selection in audience, inventory, and other campaign set ups. Our forecasting model uses deep learning models to capture the massive signal uses in execution.

The main job directions include:

• Develop ML/deep learning based models end-to-end to support various forecasting need throughout advertising campaign life cycle, including working on signal collection, feature construction, model evaluation and monitoring;
• Collaborate with engineer team on signal collection pipeline and model training, deployment and monitoring processes;
• Collaborate with downstream team to understand their forecasting needs and design appropriate models;
• Design offline and online model success metrics and use data to drive iterative model improvement

WHO WE ARE LOOKING FOR

• Proficient in machine learning (ML) and deep learning (DL). You have a strong passion for enhancing and expanding your technical skills. Your expertise includes hands-on development of ML and DL solutions utilizing open-source tools and cloud computing platforms. Has a deep understanding of the foundations of statistics and ML/DL models.

• Hands-on experience building deep learning models at large scale. A track record of partnership with a cross-functional team of data scientists, engineers and product managers to deliver AI-powered analytics or models.
• Familiar with forecasting domain with solid knowledge background and application experience. Knowledge in privacy safe measurement and data storage is a plus.

• Possessing a keen sense of data intuition and the ability to innovate in the field of model development. Have a data driven mindset and use data to drive your model development plan.

WHAT YOU BRING TO THE TABLE

We do not expect you to know every technology we use when you start at TTD. What we care most about is that you can learn quickly and solve complex problems using the best tools for the job. However, we find that the most successful candidates typically come in with something like the following experience:

• BS/MS with 8+ years or a PhD with 6+ years of experience working in a DS or ML role that involves bringing products from ideation to production.
• Experience in deep learning, PyTorch/ TensorFlow preferred.
• The ability to communicate with diverse stakeholders, making architecture recommendations, ensuring effective execution, and measuring quality of outcomes.
• Experience running heavy workloads on a distributed computing cluster (especially EMR or Databricks), leveraging technologies like Spark to work with large datasets preferred.
• Proficient in Python. Strong spark skills are a plus.
• The ability to communicate with diverse stakeholders, making architecture recommendations, ensuring effective execution, and measuring quality of outcomes.
• Experience running heavy workloads on a distributed computing cluster (especially EMR or Databricks), leveraging technologies like Spark to work with large datasets preferred.
• Proficient in Python. Strong Spark skills are a plus.