Senior AI & LLM Engineer

Eurosoft; United States; Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

Competitive salary

Direct exposure to CEO

Job summary

Eurosoft seeks a seasoned ML/NLP professional to design and deploy retrieval-augmented generation systems for enterprise use. You will build RAG pipelines, manage document processing, embeddings, and hybrid search, and evaluate generated answers to drive quality improvements.

You will also enable private LLM deployments on GPU infrastructure, serve open models with vLLM or similar, and collaborate with a small team and CEO to deliver high-impact AI solutions for clients in Korea and beyond.

Qualifications

• 5+ years of ML/NLP experience.
• 2+ years working with LLMs.
• Hands-on experience with core RAG components, including document processing and retrieval.
• Experience serving open models on GPUs.
• Familiarity with agent frameworks and tool-use patterns.

Responsibilities

• Build RAG pipelines for document parsing, embeddings, hybrid search, and reranking.
• Serve open models on GPU infrastructure using vLLM or a comparable system.
• Evaluate answer quality and improve system performance.
• Develop AI agents and tool-use workflows with LangGraph or similar frameworks.
• Support private LLM deployments for enterprise clients in South Korea.

Skills

RAG pipelines

Document processing

Embeddings

GPU deployment

LangGraph workflows

Korean residency docs

English communication

Tools

vLLM

GPU infrastructure

Job description

Role overview

Develop retrieval-augmented generation (RAG) pipelines, AI agents, and private large language model deployments for enterprise use. The role covers the path from processing and retrieving documents to serving open models on GPU infrastructure and evaluating the quality of generated answers.

Responsibilities

• Build RAG pipelines for document parsing, embeddings, hybrid search, and reranking.
• Serve open models on GPU infrastructure using vLLM or a comparable system.
• Evaluate answer quality and improve system performance.
• Develop AI agents and tool-use workflows with LangGraph or similar frameworks.
• Support private LLM deployments for enterprise clients in South Korea.

Requirements

• At least five years of machine learning or NLP experience, including two or more years working with LLMs.
• Hands-on experience with core RAG components, including document processing and retrieval.
• Experience serving open models on GPUs.
• Familiarity with agent frameworks and tool-use patterns.
• Valid Korean residency documentation and good working English; Korean is an advantage.

Benefits and work setup

• Full-time contract with market-level compensation based on experience.
• Work on private LLM and RAG platforms for enterprise clients in South Korea.
• Join a small, experienced team and work directly with its CEO.