AI Application Engineer

Job Responsibilities

1. Deploy industry-specific AI applications based on open-source and commercial large language models (GPT, Tongyi Qwen, Llama, Qwen, etc.), and implement technical solutions including prompt engineering, few-shot/zero-shot inference, and LoRA fine-tuning.

2.Build and deploy enterprise intelligent Agents based on mainstream frameworks such as LangChain, LlamaIndex, AutoGen, and Dify. Realize agent task decomposition, autonomous planning, multi-tool invocation, multi-agent collaboration, and workflow orchestration, and build intelligent assistants for enterprise office automation and business process processing.

3.Communicate and analyze business requirements, independently design AI application solutions, and complete requirement research, POC verification, prototype development, functional iteration, and online deployment and delivery.

4.Continuously optimize application experience, and resolve online production issues including model hallucinations, low answer accuracy, high response latency, excessive context length, concurrent stuttering, and abnormal Agent task execution.

5.Collaborate with front-end, product and business teams to drive project implementation, deliver standardized technical solutions, user documents and operation & maintenance manuals, and build lightweight AI backend management systems.

6.Keep track of cutting-edge AI application technologies, investigate and evaluate the implementation cost and business value of open-source models, tools, plugins and Agent frameworks, and accumulate reusable AI components and intelligent agent template libraries.

Job Requirements

1.Bachelor's degree or above in Computer Science, Artificial Intelligence, Big Data, Automation or related majors.

2.Proficient in Python and mainstream data processing tools such as Pandas and NumPy.

3.Master the full workflow of large model application development, with hands-on experience in the development and deployment of RAG systems, intelligent chatbots, document Q&A systems and enterprise Agents.

4.Possess more than 3 years of AI-related working experience with mature experience in large model application development and online project delivery.

5.Proficient in SQL, skilled in data warehouse development technologies including Hive, Spark SQL and Flink SQL, with the ability of complex indicator modeling and SQL performance tuning.

6.Familiar with mainstream big data ecosystem components, proficient in offline and real-time data development using Hadoop, Spark, Flink, Kafka and other tools.

7.Master the complete data warehouse construction system, proficient in layered modeling, dimensional modeling and indicator system design, and familiar with EDW enterprise data warehouse architecture.

8.Familiar with EDW enterprise data warehouse and big data platform architecture, with practical capabilities to connect AI applications with enterprise big data systems and empower business through data. 9.Proficient in English reading and writing fluent in Chinese is preferred to support efficient cross-team business communication and project collaboration.