Lead Data Scientist, AdTech

Launch Potato•Los Angeles, OR

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 are measured against return on ad spend (ROAS). The work involves delayed outcomes that may arrive weeks or months after a click, sparse sessions, repeat shoppers, changing market conditions, and feedback loops in which bids influence which users are acquired and therefore the data available for future training. The successful candidate will frame problems with business partners, find and prepare data, build and validate models, and own their deployment and monitoring, working alongside an ML engineer on production implementation. Auto insurance is the initial focus, with scope expected to expand to other verticals over time. The company is remote-first, and most employees work East Coast hours. Success includes independently running insurance marketplace media buying by day 60; deploying carrier conversion data in production models; bringing automated marketplace bidding from proof of concept to scale; developing approaches for repeat users and sparse sessions; and delivering production models that hold up to drift and changing objectives and are trusted and used by the business.

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 the candidate's own models in detail, including loss functions and architecture choices, and demonstrate neural network fundamentals.
Understanding that bids shape future training data, with experience handling late labels, sparse features, or drift.
End-to-end ownership of models, including finding data, building models, deployment, and monitoring.
Expert Python and SQL skills.

Nice To Haves

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

Responsibilities

Build click-wall models that match each auto insurance shopper to the carrier most likely to convert them.
Own media buying models that guide spending, bidding, or ad serving and are measured against ROAS.
Put carrier conversion data, including quotes, policies, and acquisition costs, to work in production models.
Frame data science problems directly with business partners and independently find and prepare the data needed to solve them.
Build and validate models, then own their deployment and monitoring, working with an ML engineer on production implementation.
Run insurance marketplace media buying independently by day 60.
Take automated marketplace bidding from proof of concept to scale.
Develop approaches for repeat users and sparse sessions, and ensure production models handle delayed labels, drift, and changing objectives.
Deliver model outputs that the business trusts and uses without rework.
Expand the initial auto insurance work to other verticals over time.