Lead Data Scientist, AdTech

Launch Potato•Philadelphia, NY

14d•Remote

About The Position

Launch Potato is hiring a hands-on individual-contributor Lead Data Scientist to build and operate models for its auto insurance marketplace and media buying. The role will develop click-wall models that match each auto insurance shopper with the carrier most likely to convert them, with the goal of improving partner conversion and bids. It will also own media-buying models that guide spend and are measured by return on ad spend (ROAS). Carrier conversion data—including quotes, policies, and acquisition cost—is becoming available for use in production models. The work involves delayed outcomes that may arrive weeks or months after a click, sparse sessions, repeat shoppers, and changing markets. Bidding decisions also influence which users are acquired and therefore the data available for future model training. The successful candidate will independently frame problems with business partners, locate and work with data, build and validate models, and take them through deployment and monitoring, working alongside an ML engineer on production implementation. Auto insurance is the initial focus, with scope expected to broaden 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. By the end of the first year, expected outcomes include user-to-carrier click-wall serving, production models using carrier conversion data, scaled automated marketplace bidding, a clear approach for repeat users and sparse sessions, robust production models that handle drift and changing objectives, and trusted outputs that the business can use 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 the models personally built, including loss-function and architecture choices, and neural network fundamentals.
Understanding of how bids affect future training data, with experience handling late labels, sparse features, or drift.
Experience owning models end to end, including finding data, building models, deployment, and monitoring.
Expert-level Python and SQL.

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 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 with ECS, S3, Athena, or SageMaker.
CI/CD deployment experience.

Responsibilities

Build click-wall models that match auto insurance shoppers with the carrier most likely to convert them.
Own media-buying models that guide paid media spend and are measured by ROAS.
Put carrier conversion data, including quotes, policies, and acquisition cost, to work in production models.
Independently frame problems with business partners and find and work with the relevant data.
Build and validate models, and own them through deployment and monitoring, in collaboration with an ML engineer on production implementation.
Develop approaches for delayed labels, sparse sessions, repeat shoppers, market drift, changing objectives, and bidding feedback loops.
Run insurance marketplace media buying independently by day 60 and help scale automated bidding from proof of concept.
Expand the initial auto insurance modeling scope to other verticals over time.