Staff Research Scientist - Algo Brain

The role

You will advance deep learning models for recommendations and ads. You will bring research ideas into models that run at scale and improve live production systems.

What you will do

• Find where production models for CTR, CVR and value prediction can improve
• Propose new model architectures and methods
• Design studies to prove ideas work
• Take proven improvements to production with model owning teams
• Improve how models are developed across the company
• Own model improvements end to end
• Set technical direction for a problem area
• Lead architecture changes across models and teams
• Help people grow through design reviews and mentoring

Required qualifications

• Deep expertise in machine learning and deep learning in any domain: recommendation, ads, search, NLP, vision, speech
• Track record of designing and building model architectures
• Ability to implement and train models in any framework (TensorFlow, PyTorch or others)
• Research judgment to turn open modeling problems into hypotheses and design studies
• Measurable improvements to machine learning models in production, papers at top venues (KDD, RecSys, WWW, NeurIPS or ICML), or top ranks in machine learning competitions (Kaggle, KDD Cup or RecSys Cha
• MSc or PhD in Computer Science, Mathematics, Statistics, Engineering or a related field, or equivalent research experience and expertise
• Clear written and spoken English

Nice to have

• Experience with large-scale recommendation, ads ranking or CTR/CVR prediction models
• Experience with multi-task, multi-domain or user-sequence models
• Experience defining ML experimentation and optimization methodology

Benefits

• Comprehensive benefits
• Fully stocked kitchen
• Location-specific perks

About the company

Taboola empowers businesses to grow through performance advertising technology. It reaches approximately 600M daily active users across publishers like NBC News and Yahoo.