Personalization and Recommendation Expert – Permanent

Personalization & Recommendation Expert

Position Overview

A global technology organization is seeking a Personalization and Recommendation Expert to lead research and development efforts in next-generation recommendation systems.

This role focuses on advancing large-scale personalization technologies through generative recommendation models, sequential user modeling, semantic representations, and scalable transformer-based architectures. The successful candidate will bridge cutting-edge research with production-scale recommendation systems, driving innovation across retrieval, ranking, and user behavior modeling.

Key Responsibilities

Research Leadership & Strategy

• Define and drive research directions for advanced personalization and recommendation systems.
• Focus areas include:
  • Generative recommendation
  • Sequential and long-context recommendation
  • Unified retrieval and ranking architectures
  • Foundation-model-inspired recommendation systems
• Align technical research with long-term product and business objectives.

Generative Recommendation & Sequence Modeling

• Design and develop recommendation systems that model user interactions as sequences of:
  • Events
  • Actions
  • Items
  • Semantic identifiers
• Build large-scale sequence models capable of leveraging rich behavioral histories and event streams.

Semantic Representation Learning

• Develop semantic ID and representation learning approaches, including:
  • Hierarchical and non-hierarchical semantic structures
  • Graph-informed representations
  • Learned tokenization methods
• Improve generalization and retrieval quality across recommendation tasks.

Transformer Architectures & Scalability

• Investigate efficient attention mechanisms and scalable transformer architectures for recommendation workloads.
• Study scaling behavior in recommendation systems, including relationships among:
  • Model size
  • Data volume
  • Sequence length
  • Downstream performance metrics
• Optimize systems for latency, throughput, and production efficiency.

Evaluation & Production Integration

• Design rigorous offline and online evaluation methodologies covering:
  • Ranking and retrieval metrics
  • Calibration and robustness
  • A/B testing and statistical significance
  • Business impact metrics
• Translate research innovations into production-ready systems.

Collaboration & Technical Leadership

• Collaborate across research, engineering, product, and international teams.
• Mentor researchers and engineers while promoting best practices.
• Contribute to publications, patents, technical reports, and external technical engagement.

Required Qualifications

• PhD preferred, or Master’s degree with strong research and industry experience in:
  • Computer Science
  • Machine Learning
  • Statistics
  • Mathematics
  • Related quantitative fields
• 6+ years of experience in:
  • Recommender systems
  • Personalization
  • Ranking and retrieval
  • User behavior modeling
• Strong hands-on experience in areas such as:
  • Sequential recommendation
  • Transformer-based recommendation
  • Reinforcement learning and bandits
  • Multi-task and multi-objective learning
  • Graph neural networks
  • Cross-domain or multimodal recommendation
• Deep understanding of modern recommendation architectures including:
  • Two-tower retrieval systems
  • Ranking models
  • Sequence models
  • Representation learning frameworks
• Experience building and debugging large-scale ML systems in production environments.
• Strong expertise in recommendation evaluation and experimentation methodologies.
• Proficiency with modern ML frameworks such as:
  • PyTorch
  • TensorFlow
  • JAX
• Strong communication and cross-functional collaboration skills.

Preferred Qualifications

• Experience in:
  • Generative recommendation systems
  • Semantic ID research
  • Long-sequence modeling
  • Efficient transformer attention mechanisms
  • Foundation models for recommendation
• Experience building unified retrieval and ranking architectures.
• Research into scaling laws and large-model behavior in recommendation systems.
• Publications in leading AI or recommender systems conferences.
• Experience mentoring researchers or leading technical teams.

Personal Attributes

• Strategic thinker with strong research depth and systems perspective.
• Ability to bridge advanced ML research and large-scale production systems.
• Strong analytical and experimentation mindset.
• Effective technical communicator and mentor.
• Passion for innovation in personalization and recommendation technologies.