Senior Data Scientist - Performance

Vibe.co; Paris; Sur place; EUR 90 000 - 130 000; Plein temps

Avantages offerts par ce poste

Health insurance

Meal vouchers

Annual offsite

Hybrid flexibility

Variable pay

Résumé du poste

Vibe.co recherche un Senior Data Scientist, Performance, pour rejoindre l’équipe qui optimise les résultats publicitaires des annonceurs. Vous reporterez au Head of Performance et bâtirez des modèles prod qui s’intègrent dans notre stack de diffusion et d’enchères pour CTV.

Vous travaillerez sur des données massives, du machine learning avancé et lier vos résultats à des KPI business, avec une culture d’impact et d’ambition dans un contexte hybride à Paris.

Qualifications

• Hands-on deep learning experience shipped in a professional environment.
• Strong Python skills, with PyTorch preferred; TensorFlow or JAX also fine.
• Experience diagnosing model failures: data leakage, bias, calibration, distribution shift.
• Ability to build algorithms from scratch and reason about what’s happening under the hood.
• A track record of tying your modeling work to a specific business KPI you moved.

Responsabilités

• Own the Prediction Stack and improve multi-task model predicting visits, purchases, and other outcomes.
• Design shared representations so heads learn from each other across sparse conversion funnels.
• Take ideas from exploration to production: dataset design, architecture, training, and deployment.
• Debug production models for gradient issues, convergence failures, drift, and regression.
• Partner with Performance engineers building the serving and bidding infrastructure.
• Build the Data Foundation with new features from raw signals and identity graph.
• Prepare the modeling stack to absorb richer data sources.
• Drive business impact by optimizing models for measurable advertiser uplift.
• Ship changes to production, measure results, and adjust based on outcomes.

Connaissances

Deep learning

Python

PyTorch

TensorFlow

JAX

KPI alignment

Outils

ONNX

Dagster

Triton

Description du poste

About Vibe

At Vibe.co, we're reimagining how brands reach audiences in the age of streaming. We believe streaming TV is no longer just a brand awareness play, it's the next great performance marketing channel. We're building the infrastructure to unlock this $100B opportunity.

Vibe.co provides an Audience First Streaming TV Advertising solution for marketers to unlock TV as a growth channel. Our all‑in‑one solution combines hyper‑targeted audience segmentation, AI‑powered insights and recommendations, real‑time campaign optimization, and incrementality measurement, giving brands of all sizes the precision and transparency they've come to expect from social and search, but on TV.

Trusted by over 10,000 brands, Vibe.co reaches more than 120 million households across 500+ apps and channels, delivering an average 250% return on ad spend and 20% sales lift. The company hit a $100 million revenue run rate in under two years, ranking among the ten fastest software companies to reach that milestone.

Vibe.co’s investors include Hedosophia (an early backer of Spotify, Uber, and Airbnb), Elaia, Singular, QuantumLight (Revolut CEO Nik Storonsky’s fund), and Illusian (Supercell CEO Ilkka Paananen’s fund), as well as angel investors including Carolyn Everson, board member of The Walt Disney Company and Coca‑Cola. Nirav Tolia, CEO of Nextdoor, sits on the company's board of directors.

Founded in 2022, Vibe.co is widely recognized as the category‑defining platform in streaming TV advertising, bringing the power of Meta and Google‑style performance marketing to the fastest‑growing segment in media.

Senior Data Scientist, Performance

About The Role

You’ll join the Performance team — the engineers and scientists who own advertiser outcomes at Vibe, from prediction models to bidding to the delivery stack that drives both. You’ll report to the Head of Performance. This role exists because our modeling roadmap has outgrown our current bandwidth, and the scale and diversity of data available to us is about to grow significantly. CTV performance advertising is still being invented: cross‑device attribution and identity graphs linking TVs to households look nothing like web display or search, so there’s no playbook to copy — you’ll be writing it. You’ll work with data few others have, joining CTV signal with real‑world purchase and behavioral data, which changes how we measure, attribute, and train. Vibe is growing fast enough that the model architecture is still yours to shape, and established enough that your work ships to real advertisers and shows up in the numbers within weeks.

What You’ll Do

Own the Prediction Stack

• Improve our unified multi‑task model predicting visits, purchases, and other outcomes simultaneously
• Design shared representations so model heads learn from each other across sparse conversion funnels
• Take ideas from exploration to production: dataset design, architecture, training, and deployment
• Debug production models for gradient issues, convergence failures, drift, and regression
• Partner with Performance engineers building the serving and bidding infrastructure

Build the Data Foundation

• Design new features from raw signal, including household‑level features from our identity graph
• Prepare the modelling stack to absorb new, richer data sources

Drive Business Impact

• Optimize models for measurable advertiser uplift, not offline metrics that never ship
• Ship changes to production, measure results, and adjust based on real outcomes

What You Need

• Hands‑on deep learning experience shipped in a professional environment
• Strong Python skills, with PyTorch preferred (TensorFlow or JAX also fine)
• Experience diagnosing model failures: data leakage, bias, calibration, distribution shift
• Ability to build algorithms from scratch and reason about what’s happening under the hood
• A track record of tying your modeling work to a specific business KPI you moved

Nice to Haves

• 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 identity graphs and cross‑device attribution
• Experience with production ML tooling: ONNX export, orchestration (Dagster), inference serving (Triton)

Our Values

At Vibe, we run on three values: Impact, Ambition, and Urgency. We tie every goal to a real business outcome, think 10x rather than settling for good enough, and move daily rather than waiting for perfect conditions.

You’ll thrive here if you own outcomes without needing direction, default to action, and hold yourself to results, not effort.

This is a high‑performance environment with high‑performance rewards: you’ll work alongside people who push you, with real ownership over hard problems in a market that’s moving fast.

If that sounds like the best version of your career, we want to meet you.

What We Offer

Pour les candidats basés en France, la rémunération est déterminée en fonction du marché local.

Chez Vibe, Nous Voulons Que Vous Construisiez Quelque Chose, Possédiez Quelque Chose, Et Progressiez Vite. Voici Comment Nous Le Prouvons

• Variable pay — based on objectives you hit. No arbitrary targets.
• Hybrid flexibility — We're in the Heart of Paris and our team is in 3x a week!
• Health insurance — Full coverage via Alan.
• Meal vouchers — Via Swile.
• Annual offsite — The whole team, once a year, somewhere worth the trip.
• Tech Syncs — Engineering and Product meet in person at least quarterly, worldwide.

Our Interview Process

• Recruiter screen — 30 min. We'll share context; you'll share yours.
• Manager interview — Meet the person you'd work with directly.
• Tech Interview — A real problem, not a trick. We'll work through it together.
• Calibration interview — A senior leader joins to ensure we're holding a consistent, high bar.
• Offer — Fast. We don't let good decisions sit.
• Reference checks — Two calls, handled with discretion.

Equal Opportunity

Vibe is an equal opportunity employer. We evaluate all applicants 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. We believe the best ideas come from teams with different backgrounds, perspectives, and experiences. If you need a reasonable accommodation during the application or interview process, please let us know.