tvScientific
tvScientific is the first and only CTV advertising platform purpose-built for performance marketers. We leverage massive data and cutting-edge science to automate and optimize TV advertising to drive business outcomes. Our solution combines media buying, optimization, measurement, and attribution in one, efficient platform. Our platform is built by industry leaders with a long history in programmatic advertising, digital media, and ad verification who have now purpose-built a CTV performance platform advertisers can trust to grow their business.
Write production Python that powers real-time bidding, model training, and campaign optimization
Train, deploy, and monitor ML models that decide which ads to show, when, and at what price: millions of bid decisions per second
Build and improve our incrementality measurement systems: helping advertisers understand the true causal lift of their CTV spend
Design and implement new ML products across the ad-buying lifecycle: audience targeting, bid optimization, pacing, and attribution
Use LLMs and generative AI to build internal tools that accelerate how we develop, test, and ship ML systems
Serve as a technical lead and mentor on a distributed engineering team
Strong production Python skills: you write code that runs in prod, not just notebooks
Solid statistics and ML fundamentals: you can reason about experiment design, model evaluation, and when simpler approaches beat complex ones
Familiarity with modern AI tools and good judgment about where they add value
Adtech or CTV experience: familiarity with RTB, programmatic advertising, supply-path optimization
Clear written communication: we're a distributed team and writing is how decisions get made
Comfort with ambiguity: you'll own problems end-to-end in a fast-moving environment, from scoping to shipping
Nice-to-Haves:
Teaching experience
Causal inference: uplift modeling, synthetic controls, difference-in-differences, or incrementality testing
Big data experience with Scala and Spark
Systems programming experience in Zig or similar (C, C++, Rust)
Reinforcement learning or bandit algorithms in production
Experience building agentic AI systems or LLM-powered workflows
MLOps experience: model deployment, monitoring, and pipeline orchestration on AWS
