כאן תמצאו את ג׳וב החלומות שלכם

4+ years in data science / ML applied to a data-heavy, revenue-facing domain – ad-tech, programmatic monetization, marketplaces, pricing, or a comparable real-money optimization problem.

Strong causal-inference and experimentation skills. This is the core of the role.

Fluent SQL on large event datasets and hands-on Python for modeling and analysis.

Solid grounding in the relevant ML families – regression, tree-based models, online optimization / multi-armed & contextual bandits, and classification/segmentation.

In-depth understanding of programmatic advertising from the supply side – RTB, auction mechanics, header bidding, price floors, and how publisher yield is actually made.

Ability to design experiments that measure model effectiveness in production, and to own the definitions (metrics, identity, attribution) they rest on.

Experience integrating models into production systems with engineering, in a fast, iterative environment.

Proven ability to architect and scale models processing high-volume, real-time event streams.

Excellent communication – able to turn a complex monetization result into a clear recommendation a non-technical stakeholder can decide on.

Fluent English, written and spoken.

Advantageous:

Hands-on experience with publisher-side monetization/yield optimization, header bidding, or price-floor / seller-side auction optimization specifically.

Familiarity with the Prebid stack (client & server).

Subscription/membership/LTV modeling – retention, churn, and balancing recurring revenue against ad revenue.

Working knowledge of GA4 / behavioral analytics and first-party identity resolution.

Prior experience mentoring or leading a small data-science team.