Posting Title: Reliability software engineer (Shanghai/Suzhou)

Location: Shanghai/Suzhou

Hardware reliability engineering team is looking for a talented AI and Machine
learning application engineer for our Shanghai/Suzhou reliability team. The focus of our team is to ensure that our products exceed our customer Õs expectations for robustness, durability, and reliability.
You will support building operations delivering robust and trustworthy solutions to the truly data-driven organization. In this role, you'll have the chance to apply your AI and machine
learning expertise to revolutionize data processing. Your contributions will be pivotal in maintaining the high standards of reliability that our users depend on.
.
Day-to-day responsibilities
• Develop and implement LLM-based agents that follow the Model Context Protocol (MCP) to call external tools (Python/Go SDKs).
• Fine-tune open-source LLMs (LoRA/QLoRA) on agent datasets.
• Read top-tier papers (NeurIPS/ACL/ICML) and reproduce baseline.
• results.Implement best practices from papers to production environment
• Develop data analysis toolkits to facilitate test result analysis and enginnering decision making.


Candidate will need command of these areas to help
• Proficiency in Python programming language.
• Proficiency in LLM frameworks such as LangChain, LlamaIndex, or similar tools.
• Strong knowledge in prompt engineering, agent-based workflows, and generation/manipulation of embeddings.
• Experience in setting up MCP servers and adding tools/functions.
• Proven experience in evaluating LLMs through systematic testing, benchmark design, and development of custom metrics (accuracy, consistency, factuality, bias).
Education and Experience
• MasterÕs degree or above in Computer Science, Artificial Intelligence, or a related field.
• Two years of professional experience in LLM development or integration.
• New graduates with paper(s) at top-tier venues (CVPR/ICCV/ECCV/NeurIPS/ICML/ACL, etc.)