Senior Applied Scientist

This is a fully remote position, open to applicants in United States.

📋 Description

• Design, develop, and implement machine learning solutions aimed at personalization through recommendation, retrieval, and ranking.

• Convert vague requests into scalable models and conduct experiments to produce production-ready capabilities.

• Deliver comprehensive scientific work that includes problem formulation, exploration, model development, experimentation, and deployment.

• Collaborate with platform engineering and product teams to seamlessly integrate machine learning solutions into services and workflows.

• Engage in system design and data modeling activities.

• Choose suitable methods and validate results to enhance model performance.

• Provide technical expertise to elevate scientific and engineering quality.

• Design, construct, and take ownership of feature engineering pipelines.

• Work alongside data engineering teams to refine data models that support feature engineering pipelines.

• Manage statistical measurements, perform custom tests or utilize analytics tools, and present findings to senior non-technical stakeholders.

• Write white papers, technical blog posts, and conference submissions that highlight KCL’s applied science initiatives.

⛳️ Requirements

• MS or PhD in Computer Science, Machine Learning, Statistics, Applied Mathematics, or a related quantitative discipline.

• Over 5 years of practical experience in applied machine learning with models delivered to production.

• Extensive knowledge of contemporary recommendation, retrieval, and ranking techniques, including dual-encoder retrieval, transformer-based sequence models, and learning-to-rank.

• Proficient programming skills in Python, with practical experience in PyTorch or TensorFlow.

• Experience in conducting offline evaluations and online experiments.

• Publications in recommendation conferences or a similar body of applied work (preferred).

• Familiarity with cold start recommendation, content-based or contextual models, and ephemeral item catalogs (preferred).

• Experience with session-based or sequential recommendations for anonymous or lightly-identified users (preferred).

• Knowledge of multi-objective optimization or constrained ranking (preferred).

🏝️ Benefits

• Comprehensive health insurance coverage.

• Opportunities for professional development and continuous learning.

• Flexible working hours and remote work options.

• A collaborative and innovative work environment.