Ads Recommendation Expert

Ads Recommendation Expert – Large-Scale Recommender Systems

Position Overview

A global technology organization is seeking an Ads Recommendation Expert to lead the development and evolution of large-scale recommendation systems for digital advertising platforms.

This role combines deep technical expertise in recommender systems with strategic leadership. The position focuses on advancing personalization, ranking, and optimization techniques to improve user engagement, advertising performance, and overall ecosystem growth at scale.

The successful candidate will work at the intersection of machine learning, systems engineering, and business strategy, shaping next-generation recommendation pipelines deployed across high-volume platforms.

Key Responsibilities

Recommendation System Innovation

• Design, develop, and deploy advanced recommendation algorithms for advertising applications.
• Drive innovation in areas such as:
  • Personalization and contextual ranking
  • Multi-objective optimization
  • Fairness and long-term value optimization
• Apply modern techniques including deep learning, graph-based methods, and reinforcement learning.

Model Development & Optimization

• Lead the development and improvement of core advertising models (e.g., click-through rate, conversion rate, engagement prediction).
• Optimize large-scale models, including:
  • High-parameter architectures
  • Real-time incremental learning systems
  • Sparse data scenarios
• Integrate emerging techniques such as foundation models into recommendation workflows.

End-to-End System Architecture

• Define and guide the evolution of the recommendation pipeline, including:
  • Candidate retrieval
  • Ranking
  • Post-auction optimization
• Ensure scalability, robustness, and efficiency of systems operating at large scale.

Experimentation & Evaluation

• Design and oversee A/B testing and statistical evaluation frameworks.
• Measure model performance and business impact with scientific rigor.
• Continuously iterate based on experimental insights.

Strategic Leadership & Collaboration

• Define long-term roadmap for recommendation systems aligned with business objectives.
• Collaborate with global research, engineering, and product teams.
• Act as a technical leader and mentor, promoting best practices across teams.

Research & Industry Advancement

• Stay current with state-of-the-art developments in recommender systems, including:
  • Self-supervised learning
  • Retrieval-augmented recommendation
  • Privacy-preserving and federated learning
• Translate research advances into production-ready solutions.

Required Qualifications

• PhD (preferred) or Master’s degree in Computer Science, Statistics, Mathematics, or a related field.
• At least 6 years of experience building and deploying large-scale machine learning or recommender systems.
• Strong expertise in:
  • Collaborative filtering and matrix factorization
  • Deep learning-based recommendation (e.g., transformers, GNNs)
  • Reinforcement learning or bandit algorithms
• Experience with large-scale ML frameworks (e.g., PyTorch, TensorFlow).
• Strong understanding of advertising-specific challenges, including:
  • Auction-aware recommendation
  • Multi-objective optimization (e.g., revenue, engagement, retention)
• Proven ability to design and operate production-level recommendation pipelines.
• Strong communication and cross-functional collaboration skills.

Preferred Qualifications

• Experience applying foundation models or LLMs in recommendation systems.
• Publications or contributions in top-tier conferences (e.g., RecSys, KDD, WWW, SIGIR).
• Experience with global-scale systems and high-throughput environments.
• Background in privacy-aware or federated recommendation systems.

Personal Attributes

• Strategic thinker with strong system-level vision.
• Ability to bridge research innovation with large-scale production systems.
• Strong leadership and mentoring capabilities.
• Analytical mindset with focus on measurable impact.
• Effective communicator across technical and business stakeholders.