Lead Data Scientist, AdTech

Launch Potato•Phoenix, AZ

14d•Remote

About The Position

Launch Potato is hiring a hands-on individual contributor to build and operate data science models for its auto insurance marketplace and media buying. The role will develop click-wall models that match shoppers with the carrier most likely to convert them, using carrier conversion data such as quotes, policies, and acquisition costs. It will also own media buying models that guide spend and bidding against return on ad spend (ROAS) objectives. The work involves delayed outcomes that may arrive weeks or months after a click, sparse sessions, returning shoppers, and changing market conditions. Because bids affect which users are acquired, the models also influence the data available for future training. The role frames problems with business partners, finds and prepares 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 initial focus, with scope expanding to other verticals over time. The company is remote-first, and most employees work East Coast hours.

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, including loss-function and architecture choices and neural network fundamentals.
Understanding of how current bids shape future training data, and experience handling late labels, sparse features, or drift.
Experience owning models end to end, from finding data and building models through deployment and monitoring.
Expert Python and SQL skills.

Nice To Haves

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

Responsibilities

Run the insurance marketplace media buying independently by day 60.
Build click-wall models that match each user with the carrier most likely to convert them.
Use carrier conversion data, including quotes, policies, and acquisition cost, in production models.
Own the buying models behind media spend, with performance measured against ROAS.
Develop an approach for repeat users and sparse sessions.
Take automated marketplace bidding from proof of concept to scale.
Frame problems directly with the business and identify relevant data.
Build and validate models, then support their deployment and monitoring.
Account for delayed labels, sparse features, market drift, changing objectives, and the effect of bids on future training data.
Expand the work beyond auto insurance into other verticals over time.