Lead Data Scientist, AdTech

Launch Potato

17h • Remote

About The Position

Launch Potato is hiring a hands-on individual contributor to build and operate data science models for auto insurance marketplace advertising. The role will develop models that select which carrier each auto insurance shopper sees on a click wall, with the goal of directing users to carriers most likely to convert. It will also own media-buying models that guide spend and are measured against return on ad spend (ROAS). The position will put carrier conversion data—including quotes, policies, and acquisition cost—to use in production models.

The work involves delayed outcomes that may arrive weeks or months after a click, sparse sessions, repeat shoppers, and changing market conditions. Since bidding decisions affect which users are acquired and therefore the data available for future training, the role must account for feedback effects. The scientist frames problems with business partners, sources data, builds and validates models, and follows them through deployment and monitoring, working alongside an ML engineer on production implementation.

Auto insurance will be the primary focus initially, with the scope expanding to other verticals over time. The company is remote-first, and most employees work East Coast hours. By day 60, the hire is expected to run insurance marketplace media buying independently. Within the first year, expected outcomes include carrier-matching click-wall serving, production models using carrier conversion data, scaled automated marketplace bidding, approaches for repeat users and sparse sessions, and reliable models that respond to drift and changing objectives. Outputs should be trusted and used by the business without rework.

Requirements

• At least 5 years of hands-on applied data science experience with measurable business impact.
• Experience building models that drove paid media decisions such as spend, bidding, or ad serving; attribution and reporting alone do not qualify.
• Ability to explain models personally built in detail, including loss-function and architecture choices, and neural network fundamentals.
• Understanding of how current bids shape future training data, with experience handling late labels, sparse features, or drift.
• Ability to own models end to end, from finding data through building, deployment, and monitoring.
• Expert Python and SQL.

Nice To Haves

• Experience spending real advertising budgets in live auctions.
• Experience with large-scale ranking or recommendation systems.
• Ability to explain technical tradeoffs to non-technical partners in plain language.
• Experience designing for auction feedback loops, selection bias, and exploration.
• Hands-on neural network experience, such as creating embeddings of text, creative, or user behavior.
• AWS data science experience with ECS, S3, Athena, or SageMaker.
• Experience with CI/CD deployment.

Responsibilities

• Build models that select the most suitable carrier for each auto insurance shopper on the click wall.
• Own media-buying models that guide spend and bidding and are measured against ROAS.
• Use carrier conversion data, including quotes, policies, and acquisition cost, in production models.
• Address delayed labels, sparse sessions, repeat users, market drift, and the feedback effects of bidding decisions on future training data.
• Frame data science problems with business partners and independently find and prepare relevant data.
• Build and validate models, and own them through deployment and monitoring in collaboration with an ML engineer.
• Run insurance marketplace media buying independently by day 60.
• Develop production carrier-matching and conversion models and scale automated marketplace bidding.
• Expand the work beyond auto insurance to other verticals over time.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed