Applied Data Scientist

Nift is disrupting performance marketing, delivering millions of new customers to brands every month. We're hiring a hands-on Senior Applied Data Scientist to help build and scale production-grade recommendation systems that drive our core marketplace outcomes.

This is not a research-only role. We're looking for someone who can take models from idea to production — running experiments, measuring business impact, and continuously improving the systems behind how Nift matches people with the right brands. You'll own the full lifecycle: exploratory analysis, data prep, modeling, testing, deployment, and post-launch measurement.

The ideal candidate has worked in a real production environment, brings strong deep learning experience, and understands recommendation systems in practice — not just in theory. Success here means shipping models that move Nift's core KPIs, connecting technical work to measurable business impact, and helping the team scale with strong engineering discipline.

This role is ideally based in Israel, but strong candidates in the U.S. will also be considered.

What You'll Do

• Own the full funnel of applied machine learning work, from idea through production
• Build, improve, and deploy recommendation models that support Nift's core business goals
• Tackle deep learning problems in a production setting — not just offline experimentation
• Conduct exploratory data analysis, preprocessing, feature development, and modeling
• Run experiments and evaluate success against business KPIs, not just model metrics
• Partner with engineering and infrastructure teammates to productionize models and scale systems
• Improve recommendation quality, personalization, and the business performance tied to those systems
  
  

• 5+ years of experience in production data science environments
• Strong hands-on experience taking machine learning models into production
• Strong deep learning experience; proficiency with PyTorch or TensorFlow is expected
• Direct experience with recommendation systems, or adjacent experience in areas like bidding or dynamic pricing
• Strong Python and SQL skills
• Experience working with data at meaningful scale — high-scale environments are a strong plus
• The ability to measure model success through business outcomes such as revenue, conversion, churn, or similar KPIs
  
  

• A Master's degree, especially paired with strong production experience
• A PhD paired with meaningful production-grade work (purely academic backgrounds aren't the target profile for this role)
• A software engineering background — particularly for candidates who've built pipelines and production systems before moving into machine learning