한국어·English
Moloco company · OPEN ROLE
- Company
- Sell big-platform ad prediction to every app, retailer and streamer on the open internet.
- Role
- Trace KPI drops and too-good lifts to root cause across model, data, auction and serving, then ship fixes.
Log in to mock apply, save this role or see more roles.
What you will do
We rewrote the responsibilities and qualifications in plain language instead of copying the original posting.
Responsibilities
- Traces the root cause of issues like KPI regressions, suspicious lift numbers, or cost spikes across the model, data pipeline, auction, and serving stack.
- Owns the fix, whether a feature, a reworked objective, a recalibrated model, or a changed bidding policy, through launch and the readout after.
- Designs evaluation, online and offline, that holds up in a non-stationary auction with interference and delayed conversions.
- Leaves behind methodology and tooling so other teams can answer the next version of the question.
- Communicates findings clearly to ML engineers, infrastructure, product, and account teams.
What you need
- Brings a PhD in computer science, statistics, or a comparably quantitative field with at least 2 years in the industry, or has spent 5+ years in the industry without holding a doctorate.
- Has strong applied statistics and causal reasoning skills, including experiment design.
- Is fluent in Python and SQL on large datasets (Spark, BigQuery, or similar).
- Has owned a model or algorithm in production end to end.
- Writes clearly in English.
Good to have
- Has worked in ads, recommendation, search ranking, or marketplaces with real-time bidding.
- Has handled probability calibration, delayed feedback, or selection bias in logged-bandit data.
- Has experience with CTV, attribution modeling, or incrementality measurement.
- Has used PyTorch or TensorFlow on large-scale tabular or sequential data.
Read the employer’s original job description
See how your resume reads for this role
A former Korea GM at a global company reads it and tells you what to improve for this role. It uses 1 credit.
Checked 2026-10-19
MolocoSenior/Staff Applied Scientist (시니어/스태프 응용 과학자)Start a mock application