Key Responsibilities
LLM Application Development
Architect and build applications powered by large language models, including multi-agent systems (e.g., conversational agents and workflow automation) with prompt orchestration, tool/function integration, and dependable multi-step coordination.
Implement retrieval-augmented generation (RAG) pipelines: ingestion, text chunking, embedding/indexing, vector search, reranking, and citation/attribution to ensure grounded and reliable outputs.
Design and maintain data pipelines that curate, validate, and govern external knowledge sources for LLM usage, ensuring freshness, quality, and secure access.
Enhance system performance through prompt engineering, dataset refinement, lightweight adaptation (LoRA/PEFT), and targeted fine-tuning were beneficial.
Apply LLMOps practices for deployment, monitoring, evaluation, incident handling, and iterative optimization across quality, latency, and cost dimensions.
Collaborate with ML engineers and data scientists to embed LLM capabilities into existing platforms, APIs, and downstream applications.
Stay current with advancements in the LLM ecosystem and translate emerging techniques into measurable improvements in production systems.

Qualifications & Requirements
Bachelor’s or Master’s degree in Computer Science, Mathematics, Data Science, or related disciplines (or equivalent practical experience).
At least 3 years of experience in data science or applied machine learning.
Strong programming expertise in Python, with proven experience building production-ready services (APIs, asynchronous jobs, testing frameworks, CI/CD pipelines).
Hands-on experience with LLM frameworks and libraries (e.g., LangChain/LangGraph, LlamaIndex) and modern integration approaches.
Demonstrated success in developing LLM applications and iteratively improving them through experimentation (prompt design, RAG optimization, dataset iteration, fine-tuning with PEFT).
Strong evaluation mindset: ability to define success metrics and conduct offline/online assessments (groundedness, relevance, retrieval quality, win-rate, human review, A/B testing).
Experience deploying LLM applications in production environments (containers, cloud-native architectures, scalable systems, monitoring).
Familiarity with responsible AI and security practices (privacy, access control, defenses against prompt injection, policy-aligned guardrails).
Excellent communication and teamwork skills.
Exposure to container orchestration and cloud-native deployment (e.g., Kubernetes) and observability stacks (e.g., OpenTelemetry, distributed tracing, metrics, structured logging) is an advantage.
Proficiency in both spoken and written English and Chinese.