Lead Data Scientist, AdTech

LP Careers Page

3d•$175,000 - $200,000•Remote

About The Position

Launch Potato is hiring a Lead Data Scientist to build and operate models that determine which auto insurance carrier shoppers see on its click wall, with the goal of matching each user to the carrier most likely to convert. The role also owns media-buying models used to allocate spend and evaluated on return on ad spend (ROAS). The position will use carrier conversion data, including quotes, policies, and acquisition costs, in production models. Key challenges include delayed outcomes, sparse sessions, repeat shoppers, market drift, and the feedback loop in which bidding decisions affect future training data. This is a hands-on individual contributor role. The Data Scientist frames problems with business partners, sources data, builds and validates models, and follows them through deployment and monitoring, working with 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. Launch Potato describes itself as a profitable, bootstrapped discovery and conversion company reaching tens of millions of people monthly through consumer brands in finance, travel, and entertainment. The role offers a base salary of $175,000–$200,000 per year, paid semi-monthly, plus a profit-sharing bonus and competitive benefits. Compensation varies according to the nearest major metro and the company’s Levels Framework; future increases are based on company and personal performance.

Requirements

At least 5 years of hands-on applied data science experience with measurable business impact.
Models have driven paid media decisions such as spend, bidding, or ad serving; attribution and reporting alone do not qualify.
Must have personally built the work represented on the resume and be able to explain it in depth, including loss function, architecture choices, and neural-network fundamentals.
Understand how current bids shape future training data and have handled late labels, sparse features, or drift.
Experience owning models end to end, including finding data, building models, deployment, and monitoring.
Expert Python and SQL skills.

Nice To Haves

Experience spending a real advertising budget 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 experience, such as embeddings for text, creative, or user behavior.
AWS data science experience with ECS, S3, Athena, or SageMaker.
CI/CD deployment experience.

Responsibilities

Build models that match auto insurance shoppers with the carrier most likely to convert them.
Own media-buying models that guide spend and bidding and are measured on ROAS.
Put carrier conversion data, including quotes, policies, and acquisition costs, to work in production models.
Frame problems directly with business partners and source the required data.
Build and validate models, and carry them through deployment and monitoring.
Run the insurance marketplace media buying independently by day 60.
Develop click-wall serving that matches each user to the right carrier.
Take automated marketplace bidding from proof of concept to scale.
Develop approaches for repeat users and sparse sessions and build production models that withstand drift and changing objectives.
Work alongside an ML engineer on production implementation.