Recommendation Algorithm Engineer

About the Role

We are looking for an experienced Recommendation Algorithm Engineer to design, build, and optimize large-scale personalized recommendation systems. You will develop intelligent recommendation models that deliver relevant content to users while improving engagement, retention, and overall user experience. Working closely with Product, Data Science, and Engineering teams, you will leverage machine learning and data-driven experimentation to continuously enhance recommendation quality.

Key Responsibilities

• Design, build, and optimize end-to-end personalized recommendation systems across multiple user experiences, including personalized content feeds, trending content, and category-based recommendations.
• Develop multidimensional user profiles by analyzing user behavior, including browsing, clicks, searches, follows, engagement, and interaction history, to better understand user interests and preferences.
• Design and improve the recommendation pipeline, including candidate generation, retrieval, ranking, re-ranking, cold-start strategies, diversity optimization, and real-time recommendation capabilities.
• Build scalable feature engineering pipelines by extracting meaningful features from user behavior and content data.
• Develop, train, evaluate, and deploy machine learning models to improve recommendation accuracy and overall system performance.
• Continuously optimize recommendation strategies through data analysis, experimentation, and iterative model improvements while balancing personalization, content diversity, and user satisfaction.
• Establish monitoring, evaluation, and performance measurement frameworks to ensure recommendation quality and system reliability.
• Conduct A/B testing and analyze experiment results to validate recommendation strategies and drive continuous improvement.
• Collaborate closely with Product Managers, Data Scientists, Backend Engineers, and other cross-functional teams to translate business requirements into scalable recommendation solutions.
• Stay up to date with advancements in recommendation systems, machine learning, and artificial intelligence, and introduce best practices into production systems.

Requirements

• Bachelor's degree or above in Computer Science, Artificial Intelligence, Data Science, Machine Learning, or a related discipline.
• At least 5 years of hands-on experience developing and deploying production recommendation or search systems.
• Strong understanding of recommendation system architecture, including candidate retrieval, ranking, re-ranking, multi-objective optimization, and cold-start strategies.
• Experience with machine learning and deep learning frameworks such as PyTorch or TensorFlow.
• Strong experience in feature engineering, user behavior modeling, sequence modeling, and handling sparse data.
• Proficient in designing, training, evaluating, and optimizing machine learning models using both offline and online evaluation methodologies.
• Strong analytical and problem-solving skills, with the ability to use data to identify opportunities and improve recommendation performance.
• Experience designing and evaluating A/B tests and applying experimental methodologies to optimize recommendation strategies.
• Excellent communication and collaboration skills, with the ability to work effectively across engineering, product, and data teams.

Preferred Qualifications

• Experience developing recommendation systems for large-scale consumer applications, content platforms, news feeds, media platforms, or online communities.
• Experience with vector retrieval technologies, approximate nearest neighbor (ANN) search, embedding-based retrieval, and personalized ranking algorithms.
• Experience designing user profiling, user segmentation, or user tagging systems.
• Familiarity with real-time recommendation systems, trending content algorithms, and multi-objective optimization techniques.
• Experience working with large-scale distributed data processing and machine learning infrastructure.
• Knowledge of MLOps practices, model deployment, monitoring, and continuous model optimization.