Responsibilities:
Assist clients in implementing and scaling organization-wide ML solutions across multiple business units on cloud platforms.
Transform research prototypes into production-ready pipelines, establish APIs, and ensure adherence to CI/CD standards.
Partner with infrastructure teams to guarantee systems are fully prepared for operational deployment.

Requirements:
Bachelor’s degree in Business, IT, or related fields.
Minimum of 4 years of professional experience in Data and Machine Learning.
Practical experience deploying ML models in cloud environments, including containerization (Docker) and orchestration tools.
Familiarity with agent execution and testing frameworks (LangGraph), covering run lifecycle, streaming, retries, cancellation, concurrency management, evaluation, and regression testing.
Solid backend engineering skills for chat applications (service architecture, AG-UI, API development, concurrency, and fault tolerance).
Proven experience with distributed systems and delivering production-level performance.
Understanding of LLM serving approaches: streaming outputs (SSE/WebSockets), prompt management, and graph versioning.
Experience building and integrating observability solutions (metrics, logging, tracing) for complex agent workflows/systems (Langfuse, Langsmith, Grafana, ELK).
Strong communication skills in both English and Chinese, spoken and written.

‍