At Quantcast, we’re redefining what’s possible in digital advertising. As a global Demand Side Platform (DSP) powered by AI, we help marketers connect with the right audiences and deliver measurable results across the Open Web. Our foundation is built on cutting-edge measurement and consumer analytics, giving our clients the tools they need to drive success in an ever-evolving digital landscape.
Since our start in 2006, we’ve pioneered industry firsts—from launching the original measurement platform for digital publishers to introducing the first AI-driven DSP. If you’re ready to be part of a dynamic, forward-thinking team that thrives on creating transformative solutions, Quantcast is the perfect place to grow your career.
The Modeling team is responsible for Machine Learning (ML) Systems at Quantcast and is located in London and San Francisco. We build and maintain multiple ML products. We price millions of bid requests per second in a real-time auction environment to maximize advertiser outcomes. For each bid our models predict age, gender, viewability, fraud, advertiser relevance and many more characteristics. Using NLP, clustering and LLMs we build topics in multiple languages to help our advertisers target customers interested in relevant content.
As a Machine Learning Engineer you care about the health and maintainability of our systems and the velocity of the engineering teams. You explore data, research new algorithms, experiment with proof of concepts, and build out scalable real-time production systems to tackle challenges the company faces.

• 
  
  
  
• Design, code, test, and debug ML applications and constantly improve large-scale global systems that respond to millions of real-time requests per second efficiently.

• Write clean, efficient, and maintainable code using industry best practices.
• Collaborate closely with product and platform engineering teams, to deliver high-quality ML products.
• Participate in code reviews and provide constructive feedback to team members.
• Identify performance bottlenecks and optimize system components for enhanced scalability.
• Generate and review proposals for further research and development directions.
• Keep up to date with developments in machine learning outside the company.