Senior Algorithm Engineer

Job Overview

We are establishing a pioneering AI and algorithm team within our core business units. As a Senior Algorithm Engineer, you will spearhead the design and rollout of advanced generative AI functionalities, focusing primarily on intelligent customer service chatbots, translation agents, and travel-focused conversational assistants.

This role offers significant autonomy and influence, involving end-to-end involvement in AI product innovation and guiding their extensive deployment in practical business applications. Your contributions will directly enhance user experience, operational efficiency, conversion metrics, and cost management for millions of users.

Key Responsibilities

• Lead the development and ongoing refinement of intelligent customer service chatbots and AI agents tailored for scenarios including pre-sales, travel itinerary consultations, order management, post-sales support, and multilingual translation services.
• Construct sophisticated agent frameworks encompassing task planning, tool integration, memory handling, retrieval improvements, workflow orchestration, multi-turn conversation control, and anomaly recovery techniques.
• Enhance natural language understanding and generation modules specific to travel-related and customer service contexts, focusing on intent detection, context modeling, knowledge-based Q&A, response composition, and multilingual interactions.
• Implement large-scale deployment of models within specialized verticals using strategies such as prompt engineering, retrieval-augmented generation, supervised fine-tuning, and preference optimization to boost answer accuracy, task success rates, and user satisfaction.
• Establish comprehensive evaluation frameworks for intelligent service agents, combining offline assessments, automated testing, manual quality checks, live A/B experiments, and continuous refinement protocols.
• Collaborate effectively with product management, engineering, data science, and operations teams to ensure deep embedding of AI capabilities into business systems, emphasizing high availability, minimal latency, scalability, and cost-efficiency in production.
• Continuously monitor and optimize key performance indicators like resolution rate, human escalation frequency, initial response time, average handling duration, customer satisfaction, cost-effectiveness, and system stability.

Required Qualifications and Experience

• A minimum of five years’ experience in algorithm engineering, machine learning, natural language processing, or related domains with proven large-scale AI or ML system deployment success.
• Strong hands-on expertise in generative AI and large language model applications, with deep knowledge of intelligent customer service, question answering, dialogue systems, or agent-oriented product architecture.
• Proficiency in Python programming along with familiarity in prominent ML/DL frameworks such as PyTorch, TensorFlow, and Scikit-Learn.
• Experience with technological components critical for large-scale model integration like prompt engineering, RAG, vector search, model fine-tuning, inference acceleration, tool utilization, and management of multi-turn dialogs.
• Robust engineering skills capable of independently managing the full cycle from data analysis and model experimentation through performance evaluation, to deployment and continual enhancement.
• Strong business acumen and excellent interdepartmental communication to translate advanced AI techniques into reliable, measurable, and scalable business solutions.
• Educational background of Bachelor's degree or higher in Computer Science, Artificial Intelligence, Data Science, Statistics, Mathematics, or quantitatively intensive fields.

Preferred Additional Experience

• Hands-on experience with customer service chatbots, enterprise knowledge assistants, translation agents, task-oriented dialogues, or AI copilot systems.
• Expertise in multilingual models, cross-lingual retrieval, machine translation, or internationalization efforts, notably within complex travel or service contexts.
• Familiarity with LangGraph, LangChain frameworks, ecosystems such as OpenAI, Anthropic, or open-source large model projects, and experience building multi-agent workflows.
• Knowledge in model evaluation, AI security measures, governance of AI behavior, policy controls, human-machine collaboration, and mechanisms enabling seamless transition from AI to human intervention.
• Experience with vector databases and retrieval infrastructures like Elasticsearch, Milvus, Redis, etc.
• Industry experience in OTA (Online Travel Agencies), travel, e-commerce, or high-load online service environments is advantageous.
• Exposure to search, recommendation engines, or ranking algorithms is beneficial but not mandatory.