Our client is seeking a forward-thinking LLM Engineer with high potential to join their Global Agentic AI Program. This is a high-impact role at the vanguard of the next AI frontier: Autonomous Agentic Workflows. In this capacity, you will move beyond standard chatbots to architect and deploy reliable, production-grade multi-agent systems designed to solve complex retail challenges on a global scale. As a key member of a multinational and dynamic environment, you will join a high-caliber transformation team that bridges innovation across diverse international markets. Leveraging an advanced tooling stack and LLMOps framework (including LangGraph, Langfuse, and RAG), you will build the observable, enterprise-level AI infrastructure that will define the future of "O+O" (Offline plus Online) retail.
Key Responsibilities:
• Design and orchestrate sophisticated multi-agent workflows.
• Build systems capable of multi-step coordination, complex tool/function calling, and robust error handling to ensure reliable autonomous execution.
• Develop end-to-end Retrieval-Augmented Generation (RAG) pipelines. This includes optimizing data ingestion, chunking strategies, vector indexing, and reranking to ensure high-fidelity grounding and precise citation/attribution.
• Continuously improve system output through advanced prompt orchestration, dataset curation, and lightweight model adaptation or selective fine-tuning to balance quality, latency, and cost.
• Implement rigorous monitoring and evaluation frameworks. You will manage the full application lifecycle—from deployment and tracing to incident response and iterative optimization.
• Collaborate closely with ML Engineers and Data Scientists to embed LLM capabilities into existing APIs and downstream platforms, ensuring seamless AI-to-human interaction through Generative UI components.
• Actively track the rapidly evolving LLM landscape, translating breakthrough research into measurable production improvements and use cases.
Requirements:
• Bachelor's or Master's degree in Computer Science, Mathematics, Engineering, or a related field.
• 3+ years of professional experience in AI or Data Science, with 4–8 years preferred for those seeking senior-level impact.
• A proven track record of developing and successfully deploying production-grade, LLM-powered applications.
• Expert proficiency in Python, with hands-on mastery of modern LLM frameworks and observability tools such as LangChain, LangGraph, and Langfuse.
• Deep familiarity with prompt engineering, RAG optimization, dataset iteration, and model fine-tuning.
• Strong understanding of agentic orchestration, vector databases (e.g., Pinecone, Milvus, or Weaviate), and modular, component-based AI design.
• A scientific approach to hypothesis testing—leveraging statistical data to validate the effectiveness of agent-driven strategies.
• Professional English fluency is mandatory for high-level collaboration across global markets.
