NLP / LLM Engineer

Location: Incheon, South Korea. Work style: on-site or hybrid, depending on experience.

Salary: USD 1,500–2,000 per month before taxes.

Company

HUMBLE BEE AI develops production artificial intelligence systems.

What you will do

• Design, build, and improve production NLP/LLM systems for RAG, search, AI agents, document intelligence, and multilingual NLP.
• Build retrieval pipelines with chunking, embeddings, hybrid search, filtering, reranking, indexing, and context construction.
• Develop multi-step LLM workflows and agents with routing, tool use, structured outputs, retries, and failure recovery.
• Create evaluation pipelines, run regression and A/B tests, analyze errors, and measure retrieval and generation quality.
• Reduce hallucinations while improving grounded answers, reliability, latency, token usage, inference cost, and system performance.
• Develop production APIs and services using Python, FastAPI, Docker, Git, automated testing, and CI/CD.

Requirements

• 3+ years of professional experience in NLP, machine learning, information retrieval, applied AI, or a related field.
• Strong Python engineering skills and experience maintaining production software.
• Hands-on experience deploying at least one LLM, RAG, NLP, search, or agent-based system to production.
• Understanding of transformers, tokenization, embeddings, context windows, prompting, structured generation, LLM failure modes, and advanced retrieval.
• Experience with semantic and keyword search, hybrid retrieval, filtering, reranking, chunking, indexing, and PyTorch or another modern deep-learning framework.
• Professional working English is required for technical documentation and engineering communication.

Nice to have

• Experience with BM25, RRF, Elasticsearch, Qdrant, Milvus, Pinecone, Weaviate, LangGraph, LangChain, LlamaIndex, or Graph RAG.
• Knowledge of Recall@K, MRR, nDCG, RAGAS, DeepEval, Langfuse, LoRA, QLoRA, DPO, vLLM, TGI, Triton, OCR, or multilingual NLP.
• Experience with OpenAI, Gemini, Anthropic, Hugging Face, or open-source LLM ecosystems.
• Production experience beyond prompt engineering, simple document-chat projects, API integrations, demos, or hackathons.

Culture & Benefits

• Full-time employment with compensation based on experience and demonstrated technical ability.
• Work on real production AI systems involving RAG, agents, evaluation, model adaptation, and deployment.
• Opportunity to influence architecture and technical direction.
• Direct collaboration with founders and product leadership.
• Access to high-performance compute, AI tools, and infrastructure, with opportunities for technical growth and increased responsibility.

Hiring process

• Submit a CV or resume and, if available, GitHub, portfolio, publications, or technically relevant projects.
• Describe one NLP, LLM, or search system personally built or significantly contributed to, including its problem, architecture, evaluation, failures, improvements, and production scale.