Senior Machine Learning Engineer - Personalization
Loblaw View all jobs
- Toronto, ON
- $128,000-176,000 per year
- Permanent
- Full-time
- Architect and implement advanced deep learning models for multimodal recommendation systems, processing diverse data types including text, images, user behavior, item features, offer data, and contextual signals.
- Lead the development and optimization of generative AI applications for personalized product discovery, search enhancement, and customer engagement.
- Expert in leveraging cutting-edge GenAI techniques, prompt engineering, transformer architectures, and own end-to-end development of scalable AI/ML pipelines.
- Design, build, and maintain highly scalable, robust, and efficient cloud infrastructure using Google Cloud Platform (GCP) services, including Vertex AI, BigTable, BigQuery, AlloyDB, and Cloud Composer.
- Develop automation and orchestration of ML pipelines, integrating data ingestion, feature engineering, training, and deployment processes.
- Collaborate with cross-functional teams to understand their needs and build solutions that improve platform usability, scalability, and the overall development experience.
- Optimize data processing pipelines and cloud resources to ensure low-latency, cost-effective operation.
- Implement monitoring, alerting, and failover strategies to ensure platform reliability.
- Stay updated with industry trends and best practices in cloud engineering, data engineering, and machine learning
- Master's or PhD in Computer Science, Machine Learning, or related field.
- 8+ years of experience in machine learning engineering, with a focus on recommendation systems or personalization.
- Strong expertise in deep learning frameworks (PyTorch or TensorFlow) and building production-grade ML systems.
- Proven experience with GCP services and ML infrastructure at scale.
- Proficient in Python, SQL, and cloud-native development.
- Experience with containerization (Docker) and orchestration (Kubernetes).
- Track record of deploying ML models to production at scale.
- Experience with multimodal deep learning architectures and generative AI models.
- Knowledge of modern recommendation system architectures (transformers, neural collaborative filtering).
- Expertise in building real-time inference systems.
- Experience with distributed computing frameworks (Spark) and big data processing.
- Familiarity with Apache Airflow (Cloud Composer) and CI/CD pipelines.