- Remote, Canada
- Remote
- Full-time · Staff
- 3+ years
Build, train, and deploy next-generation LLM-based recommender systems, covering the full path from raw customer data to a deployed model.
Responsibilities
- Turn structured and unstructured traveler and catalog data into narrative text documents and synthetic data
- Make the feature and context engineering decisions
- Run large-scale distributed training on Amazon SageMaker AI, including HyperPod
- Fine-tune models with LoRA/QLoRA adapters, supervised training, and reinforcement learning for ranking and reasoning
- Own deep learning modeling, including architecture, ranking heads, and co-training and multi-task setups
Requirements
- Nice to have: AWS Trainium
- Nice to have: AWS Inferentia
- Nice to have: Neuron SDK
- Nice to have: Recommender systems
- Nice to have: NDCG