Remote job
Senior AI va LLM muhandis
Job details
About this role
Role overview Develop retrieval-augmented generation pipelines, AI agents, and private LLM solutions for enterprise customers. The work spans document processing and search, model deployment, agent tooling, and evaluating the quality of generated responses.
Responsibilities - Build RAG pipelines covering document parsing, embeddings, hybrid search, and reranking. - Deploy open models on GPU infrastructure using vLLM or a comparable serving approach. - Evaluate response quality and use findings to improve system performance. - Create AI agents and tool integrations with LangGraph or a similar framework. - Deliver private LLM capabilities for enterprise use.
Requirements - At least five years of experience in machine learning or natural language processing, including at least two years working with LLMs. - Practical knowledge of RAG components, including document parsing, embeddings, hybrid retrieval, and reranking. - Experience serving open models on GPUs and assessing generated responses. - Experience building agents and tools with LangGraph or a comparable framework. - Current authorization to live in South Korea, documented with a residence or ID card. - Working English; Korean is an advantage.
Benefits and work setup - Full-time employment and compensation aligned with the market and the candidate’s experience. - Work with a small, senior team and have direct access to the company’s chief executive. - Develop private LLM and RAG platforms for enterprise customers in South Korea.