AI Machine Learning Engineer

About the team Our Search Team is responsible for building and owning our search engine which provides our users the best search experience. In our Search Team, you’ll have the opportunity to build a full-stack search engine system and combine information retrieval technology with modern machine learning methods from related fields such as NLP, Computer Vision, Multimodal, and Recommender Systems. We embrace a culture of self-direction, intellectual curiosity, openness, and problem-solving. Responsible for the Search Top-1 Card and AI Assistant features in Lemon8 product. Leverage in-platform content and users' historical conversations as contextual inputs to deliver a personalized, highly authentic tool-based product through conversational interaction.In the conversational search paradigm, accurately identify user intent by combining real-time dialogue context and historical chat memory. Integrate high-quality in-platform UGC content with authoritative global knowledge to generate authentic, traceable AI-powered results. Core Responsibilities: 1. End-to-End AI Agent System Construction: Lead the full lifecycle delivery of AI Agent applications, from offline MVP prototyping to production-grade closed-loop systems. Own the design and implementation of foundational data pipelines, core workflow architectures, service execution layers, and observability frameworks to ensure system scalability, stability, and performance. 2. Business Outcome-Driven Engineering Iteration: Drive algorithmic and strategic optimizations aligned with business objectives. Oversee core business pipeline launches and iterations via offline batch runs, A/B testing, and online canary deployments, continuously improving user experience, system efficiency, and key business metrics. 3. Quality Assurance & Evaluation System Establishment: Build end-to-end quality validation mechanisms covering data processing, reasoning, and generation. Develop offline evaluation frameworks, bad case taxonomies, and automated assessment pipelines to guarantee the accuracy, consistency, and compliance of business outputs. 4. Intelligent Capability Evolution & Cross-Scenario Expansion: Own the iteration and optimization of core intelligent capabilities including multi-step reasoning, RAG, and personalized memory systems. Drive the reuse and deployment of Agent technologies across vertical business scenarios to support long-term intelligent business upgrades. Minimum Qualifications 1. Bachelor's degree or above in a computer-related major, with excellent coding ability and proficient in programming languages such as C++/Python, and familiar with common data structures and programming algorithms. 2. Proficient in C++/Python; strong command of algorithms and data structures (e.g., retrieval, graph algorithms). 3. Basic understanding of LLM fundamentals (e.g., prompt engineering, fine-tuning workflows). 4. Strong problem-solving skills with a track record of delivering technical projects. Preferred Qualifications 1. Hands-on experience with LLM/Agent technologies: RAG optimization, RLHF/SFT for LLMs, or Agent framework development (e.g., planning/memory modules). 2. Excellent communication and collaboration skills, with a track record of exploring new technologies and driving technical advancements with teams.