Data Scientist

Data scientists at TTD work closely with engineering throughout the lifecycle of the product, from ideation to productionization 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.

We are looking for a Senior Data Scientist to design, build, and scale data driven solutions powering our
forecasting, pacing, and recommendation systems for our emerging channels. You will develop advanced machine learning or deep learning models that directly influence planning, allocation and performance on our platform.

• Develop forecasting models using statistical, ML and deep learning approaches.
• Build and optimize pacing algorithms
  that balance short-term performance with long-term objectives and constraints.
• Build custom solutions tailored to our unique environment, where off-the-shelf models often don't scale effectively.
• Collaborate with product teams to understand business goals and translate them into actionable data science solution.
• Work closely with engineering teams to deploy models from prototype to production, ensuring smooth integration into products.
• Define success metrics, conduct offline evaluation and online experiments (A/B testing), and measure business impact.
• Communicate technical results and tradeoffs clearly to technical and non‑technical audiences.

• Proficient in open‑source languages, you have a strong passion for enhancing and expanding your technical skills. Your expertise includes hands‑on development of predictive models and solutions utilizing open‑source tools and cloud computing platforms. Has a deep understanding of the foundations of statistics and machine learning
• Hands‑on experience building data science solutions at scale. A track record of owning a project end‑to‑end (from research to production), and partnership with a cross‑functional team of data scientists, engineers, and product managers to deliver the data science solution and models

We do not expect you to know every technology we use when you start t 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 5+ years or a PhD with 3+ years of experience working in a DS and ML role that involves bringing products from ideation to production.
• Experience in building ML model in always‑on production system and working with diverse technologies and data sources
• Strong experience in one or more of:
  forecasting, pacing systems, or recommendation systems.
• Proficient in Python
• Hands‑on experience with deep learning frameworks (PyTorch, Tensor Flow).
• Experience running heavy workloads on a distributed computing cluster (especially EMR or Databricks), leveraging technologies like Spark to work with large datasets.
• Experience in programmatic advertising and/or real‑time auctions is preferred

CO, CA, IL, NY, WA, and Washington DC residents only: In accordance with CO, CA, IL, NY, WA, and Washington DC law, the range provided is The Trade Desk's reasonable estimate of the base compensation for this role. The actual amount may differ based on non‑discriminatory factors such as experience, knowledge, skills, abilities, and location. All employees may be eligible to become The Trade Desk shareholders through eligibility for stock‑based compensation grants, which are awarded to employees based on company and individual performance.

The Trade Desk also offers other compensation depending on the role such as sales‑based incentives and commissions. Plus, expected benefits for this role include comprehensive healthcare (medical, dental, and vision) with premiums paid in full for employees and dependents, retirement benefits such as a 401k plan and company match, short and long‑term disability coverage, basic life insurance, well‑being benefits, reimbursement for certain tuition expenses, parental leave, sick time of 1 hour per 30 hours worked,…