About The Team
The Marketplace Intelligence and Data team's mission is to build sustainable and efficient data and intelligence products to facilitate Shopee's business development. The team is responsible for Shopee e-commerce data warehouse construction, merchant and operation data product construction, all-link traffic data, product algorithms, including product release, control, information optimization, SPU library and its comparison business, marketing algorithms, including Merchandising, Product Selection, Recommendation Algorithm, Evaluation Algorithms, User Profiling, and in addition, basic AI capabilities, such as Machine Translation, Speech Algorithm, Image Algorithm, and Real-person Authentication.
We are the Customer Service Chatbot team at Shopee Singapore, committed to developing multilingual, intelligent dialogue systems that serve a wide range of consumers and sellers. Our focus lies in applying advanced AI technologies - including recommendation systems, Large Language Models (LLMs), autonomous agents, and reinforcement learning - to customer service scenarios, continuously enhancing interaction quality and user experience.
Job Description
Our team aims to apply LLM/Agent technology to our recommendation system and Agent Auto Quality Assurance, thereby improving service satisfaction and efficiency for chatbots and agents. Your scope will include, but not be limited to:
- Generative RecSys: Design and develop core components of the chatbot's recommendation, adopting the thought of a generative model (e.g. LLM reasoning/scaling law) to improve CTR of RecSys.
- Proactive Support Agents: Modeling user's CS behaviour based on user profiles and historical interaction data to recognise users real intent and answer it proactively.
- Feature Insight Agents: Automatically reason potential features and defining user's event from Agent-Human dialogues.
- AutoQA Agent: Build an in-domain LLM with SFT for long context and design memory context management to check the agent service quality automatically.
Requirements
- Currently pursuing a Bachelor's degree or above in Computer Science, Artificial Intelligence, or a related discipline.
- Solid experience with optimisation of end-to-end RecSys, including retrieval-ranking systems, Deep Learning RCMD (e.g., xDeepFM, DIN, MMoE), as well as LLM-based generative recommendation models (e.g., HSTU, OneRec, RankMixer).
- Proficient in Python and experienced with deep learning frameworks such as PyTorch or TensorFlow.
- Strong analytical and problem-solving abilities, with a passion for building intelligent, user-centric products.
- Experience in training and fine-tuning large language models using techniques such as supervised fine-tuning (SFT) or reinforcement learning (RL).
- Prior experience developing or optimising algorithms for large-scale recommendation, search, or advertising systems.
- Experience in chatbot algorithm development is a strong plus
