Lead Data Scientist, AdTech

Launch Potato; Valparaíso; Hybrid; CLP 137,525,000 - 196,464,000; Full time

Job summary

Launch Potato is seeking a senior data scientist to own end-to-end ML models that optimize insurance marketplace decisions and media buying. You will identify data, build production-grade models, validate performance, and monitor drift in a fast-paced, remote-first environment across multiple countries.

You will work with an ML engineer on deployment and scaling, handling complex feature sets, late labels, and evolving objectives while ensuring measurable impact and ROAS improvement.

Qualifications

• 5+ years hands-on data science with measurable business impact.
• Models used to drive paid media decisions: spend, bidding or ad serving; attribution and reporting not sufficient.
• Built and explained model architectures, loss functions and training data considerations.
• Handled late labels, sparse features or drift in dynamic environments.
• End-to-end ownership from data discovery to deployment and monitoring.

Responsibilities

• Frame business problems and identify data to address them.
• Build and validate production ML models for insurance marketplace decisions.
• Deploy and monitor models; collaborate with ML engineers on the production side.
• Own data pipelines and validation to support scalable bidding and targeting.
• Iterate models as market conditions evolve and ensure measurable impact.

Skills

Data science

Machine learning

Modeling

Python

SQL

Education

Bachelor's or higher in a quantitative field

Tools

AWS SageMaker

AWS ECS

S3

Athena

Python

Job description

Our mission: create predictable, high-value customer acquisition at scale by connecting discovery, intent, and performance across category-leading consumer brands in finance, travel, and entertainment.

We run profitable and bootstrapped, with a South Florida HQ and a remote-first team across 18 countries.

WHY JOIN US?

You own outcomes here, not tasks. We measure work by impact, not activity. The pace is real, and change is constant, so the people who do best turn change into opportunity instead of waiting for it to settle. Feedback runs direct and lands with respect. Ordinary people make themselves extraordinary at Launch Potato.

YOUR ROLE

You'll build the models that decide which carrier each auto insurance shopper sees on our click wall. The goal is to send every user to the carrier most likely to convert them, so carriers see our traffic convert and raise their bids. You'll also own the buying models behind our media spend, which are held to ROAS.

Carrier conversion data (quotes, policies and acquisition cost) is now coming back to us, and you'll be the one who puts it to work in production. The hard part is the data. Outcomes land weeks or months after the click, many sessions are sparse, the same shoppers come back, and the market drifts. Our bids also decide which users we win, so the model shapes the data it learns from next.

This is a hands-on individual contributor role. You frame problems directly with the business, find your own data, build and validate the model, and stay with it through deployment and monitoring. An ML engineer works alongside you on the production side. Auto insurance takes most of your time to start, and scope broadens to other verticals over time.

We're remote first, and most of the company works East Coast hours.

WHAT SUCCESS LOOKS LIKE

By day 60, you run our insurance marketplace media buying on your own.

By the end of your first year:

• Click wall serving that matches each user to the right carrier


• Automated marketplace bidding taken from proof of concept to scale


• A clear approach for repeat users and sparse sessions


• Production models that hold up through drift and changing objectives


• Output the business trusts and uses without rework

MUST HAVE

• 5+ years of hands-on applied data science with measurable business impact


• Your models drove paid media decisions: spend, bidding or ad serving. Attribution and reporting alone don't qualify.


• You built what's on your resume and can explain it down to the loss function and architecture choice, neural network fundamentals included


• You see how today's bids shape tomorrow's training data, and you've handled late labels, sparse features or drift


• You own models end to end: you find your own data, build through deployment and monitoring, and bring a point of view


• Expert Python and SQL

NICE TO HAVES

• Real ad budget spent in live auctions


• Large-scale ranking or recommendation systems


• Explaining tradeoffs to non-technical partners in plain terms


• Designing for auction feedback loops, selection bias and exploration


• Hands-on neural network work, such as embeddings of text, creative or user behavior


• AWS for data science: ECS, S3, Athena, SageMaker

Since day one, we've been committed to having a diverse, inclusive team and culture. We are proud to be an Equal Employment Opportunity company. We value diversity, equity, and inclusion.

We do not discriminate based on race, religion, color, national origin, gender (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender identity, gender expression, age, status as a protected veteran, status as an individual with a disability, or other applicable legally protected characteristics.