Shopee Hiring! Full Time [AI] Agentic Commerce AI Agent Algorithm Engineer in - Ricebowl

About The Team

About Us

Sea Group is establishing a brand-new, strategic AI department. This department is dedicated to exploring the transformative potential of generative AI in revolutionizing human connection, self-expression and communication diversity, and social interaction. We are building the next generation of AI-native applications and a comprehensive Model-as-a-Service (MaaS) product support system. Based on massive multi-country data, we are building a leading multilingual AI ecosystem from the ground up. We look forward to more outstanding talents joining us to build leading Southeast Asian multilingual models and explore innovative AI-native applications.

The AI application team focuses on the intersection of social connectivity and artificial intelligence. Our mission is to leverage LLMs to create digital personas that can act as personal assistants and social bridges. This team operates with a startup's agility backed by our Group's robust resources, aiming to define how humans interact in the AI era.

Job Description

• E-commerce shopping Agent architecture design: Design a shopping Agent for To C (consumer) users, covering intent understanding, task planning, product recall, tool calling, result integration, and multi-turn conversation pipelines.
• User intent and requirement understanding: Address natural language queries, ambiguous requirements, scenario-driven shopping, budget constraints, and preference expression to improve the Agent's ability to interpret users' real shopping intent.
• User memory and preference modeling: Build long- and short-term memory systems for e-commerce scenarios based on user conversation and behavioral data, model user preferences, and enhance the Agent's personalization capabilities.
• Tool-calling capability improvement: Design and optimize the strategies and pipelines for the Agent invoking tools such as search, recommendation, product details, review summarization, price comparison, promotions, inventory, and logistics.
• Multi-turn guided shopping dialogue: Build multi-turn dialogue capabilities for complex shopping decisions, including need clarification, preference follow-up, product filtering, candidate comparison, and purchase recommendation generation.
• Agent evaluation and effectiveness optimization: Build offline and online evaluation systems covering task completion rate, product relevance, recommendation accuracy, factual consistency, hallucination rate, conversion metrics, user satisfaction, latency, and cost.
• Online deployment and continuous iteration: Collaborate with product, engineering, search/recommendation, merchandising, and operations teams to drive large-scale application of Agent capabilities in company-wide To C scenarios.
  
  

Requirements

• Master‘s degree in Computer Science, Artificial Intelligence, Mathematics, Software Engineering, or a related field.
• At least 3 years of full time experience in algorithms, machine learning, NLP, search & recommendation, or LLM applications, including at least 1 year of hands-on practice with large model applications or dialogue systems.
• Prior development experience with at least one of the following directions: Agent orchestration, Agentic Search, Memory, Agentic RL.
• Prior experience with LLM application development paradigms, including Harness Engineering, Function Calling, context management, and LLM Eval.
• Strong proficiency in Python; able to drive algorithm solutions from experimental validation to online deployment.
• Strong understanding of To C product requirements for experience, latency, cost, stability, and security, with the ability to continuously optimize Agent effectiveness in real online scenarios.
• Strong business understanding, data analysis, problem decomposition, and cross-team collaboration capabilities.
• Prior hands-on experience with e-commerce guided shopping, intelligent shopping assistants, search/recommendation Copilots, or To C AI products in production will be a storng plus
• Prior experience with evaluation, A/B experiments, cost optimization, latency optimization, and stability governance for large-scale online LLM applications.
• Prior experience with Agent frameworks or complex workflow orchestration, such as Google ADK, LangGraph, OpenAI Agents SDK, etc.
• Experience with Agentic SFT / RL training is a plus.