Senior Data Scientist – Performance

About This Opportunity

We are representing a confidential streaming TV advertising platform based in Paris. Our client operates at the intersection of connected TV and performance marketing, building technology that brings digital precision to television advertising. They work with thousands of brands and reach over 100 million households through targeted, measurable campaigns.

We're seeking a Senior Data Scientist to join their Performance team. This role owns the prediction models, bidding algorithms, and delivery systems that drive advertiser outcomes. You'll work with unique datasets linking connected TV signals to real-world behavioral and transactional data, building multi-task models that predict visits, purchases, and conversions across sparse funnels. The modeling architecture is still being shaped, and your work will ship to production within weeks of development.

Responsibilities

• Own and improve the unified multi-task prediction model for multiple conversion outcomes
• Design shared representations that enable model heads to learn from each other across the funnel
• Take modeling projects from exploration through production deployment, including dataset design, architecture, training, and serving
• Debug production models for gradient issues, convergence failures, drift, and regression
• Partner with performance engineers on serving and bidding infrastructure
• Design new features from raw signal, including household-level features from identity graphs
• Prepare the modeling stack to absorb new, high-volume data sources
• Optimize models for measurable advertiser uplift rather than offline metrics alone
• Ship changes to production, measure real outcomes, and iterate based on results

What We're Looking For

Required:

• Hands-on deep learning experience delivered in a professional production environment
• Strong Python skills; PyTorch preferred (TensorFlow or JAX also acceptable)
• Demonstrated experience diagnosing model failures including data leakage, bias, calibration, and distribution shift
• Ability to build algorithms from scratch and reason about underlying mechanics
• Track record of connecting modeling work to specific business KPIs and measurable impact

Preferred:

• Experience with massive-scale datasets (billions of impressions, events, or user records)
• Deep learning on tabular data and sparse user representations
• Background in CTR/CVR prediction, recommendation systems, or cross-device attribution
• Experience with production ML tooling such as ONNX export, orchestration frameworks, or inference serving platforms

How We Work With You

Candidates apply directly through Get A Job.ai. Our recruiting team will conduct an initial screen to understand your background and confirm alignment with the role. If there's a strong match, we'll submit your profile to our client for consideration. The client's process includes a manager interview, a technical problem-solving session, and a calibration interview with senior leadership. Reference checks are handled discreetly at the final stage.

Please do not contact the client directly. All communication and coordination will flow through our talent team at Get A Job.ai to ensure a professional, structured process.

Our client offers equity participation, performance-based variable pay, hybrid work from their central Paris office (three days per week), full health coverage, meal vouchers, annual team offsites, and quarterly in-person technical syncs. They will support relocation to Paris for the right candidate.

Pay

Compensation details will be discussed during the screening process based on experience and qualifications.

Equal Opportunity: Get A Job.ai is an equal opportunity recruiter. We evaluate all candidates without regard to race, color, religion, national origin, gender, gender identity or expression, sexual orientation, age, disability, veteran status, or any other characteristic protected by law.