Large Recommendation Model Algorithm Engineer - Global E-Commerce Singapore Regular

Pangleglobal; Singapore; On-site; SGD 80,000 - 120,000; Full time

Job summary

Pangleglobal in Singapore seeks a Large Recommendation Model Algorithm Engineer. This role focuses on building advanced recommendation systems using machine learning and deep learning, specifically applying LLM technologies. Responsibilities include optimizing Foundation Models and exploring multimodal understanding within recommendation paradigms. Candidates should have a strong background in Python and a passion for intelligent systems. Preferred qualifications include experience in large-scale systems and research in LLMs or reinforcement learning.

Qualifications

• Solid theoretical foundation in machine learning, deep learning, or information retrieval.
• Proficiency in Python and familiarity with mainstream deep learning frameworks like PyTorch.
• Strong passion for intelligent recommendation systems and a self-driven research mindset.

Responsibilities

• Build and optimize cross-scenario shared Foundation Models for unified modeling.
• Apply LLM technologies across retrieval and ranking stages.
• Explore the integration of LLMs with recommendation systems.
• Research generative recommendation and system optimization methods.

Skills

Machine learning

Deep learning

Python

Information retrieval

Tools

PyTorch

Job description

Large Recommendation Model Algorithm Engineer - Global E-Commerce

About the TeamThe E-commerce Recommendation Foundation team is dedicated to building the next-generation recommendation intelligence. We aim to develop a unified Foundation Model that supports multi-business and multi-scenario recommendation systems, covering the full pipeline from retrieval and ranking to re-ranking, and driving a comprehensive upgrade in intelligence and generative capability. We believe the future of recommendation systems goes beyond predicting click-through rates — it lies in understanding the relationship between people and content, and in generating new connections. The team is exploring an event-sequence-driven generative recommendation paradigm, deeply integrating large language models (LLMs), multimodal understanding, reinforcement learning, and system optimization to advance recommendation systems toward general-purpose intelligent agents. We value original exploration and encourage both research thinking and engineering excellence. Every team member is empowered to propose hypotheses and validate ideas in an open environment — your code and papers may help define the next paradigm of recommendation systems. We seek individuals with a general intelligence mindset to join us in redefining the future of recommendation.

Responsibilities

• Build and optimize cross-scenario shared Foundation Models to enable unified modeling and efficient inference. Advance the event-sequence-driven generative recommendation paradigm, integrating multimodal understanding and generative capabilities.
• Apply LLM technologies across retrieval, ranking, and re-ranking stages; participate in model training, inference optimization, and system co-design.
• Explore the integration of LLMs / VLMs with recommendation systems to develop adaptive and evolving intelligent recommenders.
• Research end-to-end generative recommendation and system optimization methods that balance efficiency and user experience.

Minimum Qualifications

• Solid theoretical foundation in machine learning, deep learning, or information retrieval.
• Proficiency in Python and familiarity with mainstream deep learning frameworks (e.g., PyTorch).
• Strong passion for intelligent recommendation systems and a self-driven research mindset.

Preferred Qualifications

• Experience in large-scale recommendation system development or large-model training, with notable technical achievements in a sub-area.
• Research experience or publications in LLMs, multimodal learning, reinforcement learning, or generative recommendation.
• Familiarity with pre-training and post-training processes for large language models (LLMs) or Foundation Models.