Staff Applied Scientist, AdTech

About the role

Launch Potato is a discovery and conversion company that reaches tens of millions of people monthly through its brands, including FinanceBuzz, All About Cookies and OnlyInYourState. It connects discovery, intent and performance across consumer brands in finance, travel and entertainment, and runs a remote-first team across 18 countries. This is a hands-on individual contributor role focused on building the models that decide which carrier each auto insurance shopper sees on the click wall, aiming to send every user to the carrier most likely to convert.

Key responsibilities

• Build and deploy models that match each user to the carrier most likely to convert, so carriers see more conversions and raise their bids.
• Own the buying models behind media spend, held to ROAS, using carrier conversion data (quotes, policies and acquisition cost).
• Work with data that arrives weeks or months after the click, with sparse sessions and returning shoppers; the model shapes the data it learns from next.
• Frame problems directly with the business, find your own data, build and validate the model, and stay with it through deployment and monitoring.
• An ML engineer works alongside you on the production side.
• By day 60 run the insurance marketplace media buying on your own; by the end of year 1 deliver production models, automated bidding at scale, and a clear approach for repeat users and sparse sessions.

Required profile

• 5+ years of hands-on applied data science with measurable business impact.
• Models that drove paid media decisions (spend, bidding or ad serving); attribution and reporting alone do not qualify.
• Experience handling late labels, sparse features and drift, and owning models end to end.
• Remote-first, with most of the company working East Coast hours.

Required skills

• Expert Python and SQL
• Nice to have: large-scale ranking or recommendation systems, neural networks (embeddings of text, creative or user behavior)
• Nice to have: AWS for data science (ECS, S3, Athena, SageMaker) and CI/CD deployment