Ebay Senior Applied Researcher 

Canada, Ontario, Toronto 

766451654

We are working on challenges such as:

• Building recommender systems that surface the most relevant listings based on user behavior, context, and item signals.

• Developing personalized banners, dynamic landing pages, and real-time ranking models for buyer experiences.

• Integrating structured data, text, and images to deliver rich, context-aware personalization.

• Running large-scale experiments to measure and optimize conversion, engagement, and satisfaction.
  

• Design, develop and productionize machine learning models for personalization, recommendation, and ranking.

• Build scalable systems that deliver real-time buyer experiences across millions of users and inventory listings.

• Conduct A/B experiments and use data-driven insights to iterate and optimize models.

• Work closely with product managers, engineers, and designers to integrate science-driven features into the buyer experience.

• Document and communicate technical approaches, insights, and results to technical and business audiences.

• Contribute to the science strategy by identifying new opportunities and approaches based on data trends and business goals.

What you will bring :

• 5+ years of industry experience applying machine learning at scale, ideally in recommendation, ranking, or personalization domains.

• MS or PhD in Computer Science, Machine Learning, Statistics, or a related technical field.

• Strong programming skills in Python and experience with ML frameworks such as PyTorch or TensorFlow.

• Experience working with large datasets and distributed computing frameworks like Spark or Hive.

• Strong background in experimental design, A/B testing, and statistical analysis.

• Experience in ecommerce, online marketplaces, or consumer-facing applications.

• Knowledge of multimodal machine learning techniques (e.g., using structured data, text, and image signals together).

• Familiarity with recommender system architectures, ranking algorithms, or retrieval systems.

• Experience building models that prioritize privacy, fairness, and user trust.