Staff Data Scientist, Lead Generation

launchpotato; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Remote-friendly with East Coast hours

Profit-sharing bonus

Competitive benefits

Job summary

launchpotato is seeking an experienced data scientist to own applied data science for an insurance marketplace ranking and paid media buying. You will build models that match shoppers to carriers and optimize media spend toward ROAS goals.

This hands-on role covers problem framing through deployment and monitoring, with an ML engineer supporting production. You will work with business partners to explain model decisions and adapt to delayed outcomes and evolving market conditions.

Qualifications

• Five or more years of applied data science with measurable business results.
• Experience building models that influence paid media spend or ad bidding.
• Ability to explain model architecture and neural network fundamentals.
• Experience owning models end to end from data through deployment and monitoring.
• Understanding delayed outcomes, sparse features, market drift.

Responsibilities

• Develop and improve models matching shoppers to likely-converting carriers and inform paid media spend and bidding.
• Bring quote, policy, and acquisition-cost outcomes into production models, accounting for delayed labels and incomplete sessions.
• Address repeat users, sparse data, changing market conditions, and the feedback effects of bids on future training data.
• Take models from analysis and validation through production monitoring, with attention to performance and changing objectives.
• Establish a scalable approach to automated marketplace bidding and expand the work beyond insurance over time.
• Communicate model decisions and tradeoffs so business partners can use the resulting systems with confidence.

Skills

Applied data science

Python

SQL

End-to-end model ownership

Model deployment

Paid media / bidding modeling

Tools

AWS SageMaker

S3

Athena

ECS

CI/CD deployment

Job description

Role overview

Own applied data science for insurance marketplace ranking and paid media buying. You will build models that select the most promising carrier for each shopper and guide media spend against return-on-ad-spend goals, using conversion outcomes that may arrive weeks or months after an interaction. This is a hands-on individual contributor role: you will work directly with business partners from problem framing through data discovery, model development, validation, deployment, and monitoring, alongside an ML engineer supporting production implementation.

Responsibilities

• Develop and improve models that match shoppers to likely-converting insurance carriers and inform paid media spend and bidding.
• Bring quote, policy, and acquisition-cost outcomes into production models, accounting for delayed labels and incomplete sessions.
• Address repeat users, sparse data, changing market conditions, and the feedback effects of bids on future training data.
• Take models from analysis and validation through production monitoring, with attention to performance and changing objectives.
• Establish a scalable approach to automated marketplace bidding and expand the work beyond insurance over time.
• Communicate model decisions and tradeoffs so business partners can use the resulting systems with confidence.

Requirements

• Five or more years of applied data science experience with measurable business results.
• Experience building models that directly influence paid media spend, bidding, or ad serving; attribution and reporting alone are insufficient.
• Strong command of Python and SQL, and the ability to explain model architecture, loss functions, and neural network fundamentals.
• Experience owning models end to end, from finding and preparing data through deployment and monitoring.
• Understanding of delayed outcomes, sparse features, market drift, or the way decisions affect the data collected for future training.

Nice to have

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

Benefits and work setup

• Remote-first work, with most colleagues working East Coast hours.
• Compensation includes a base salary, profit-sharing bonus, and benefits; the base is set by market and level, and future increases are tied to individual and company performance.