2 days ago
Seoul, Korea, SouthSenior
Responsibilities
- Design and build LLM, multi-agent, RAG, and tool-calling applications to automate catalog operations.
- Design, implement, and operate highly available and scalable backend systems for large-scale real-time and batch data processing.
- Build AI pipelines for product information extraction, classification, attribute mapping, duplicate detection, and automated correction of anomalous data.
- Integrate LangChain, LlamaIndex, AutoGen, and related AI orchestration frameworks with existing backend domain services.
- Monitor and optimize latency, throughput, API costs, and token consumption for large-scale LLM inference and backend services.
- Collaborate with Product Managers, Data Scientists, Machine Learning Engineers, and domain experts to define and deliver AI-based product requirements.
Requirements
- Bachelor’s degree or higher in Computer Science, Computer Engineering, or a related field.
- At least 3 years of backend system design and development experience using technologies such as Java, Kotlin, Python, or Go.
- Production experience developing and commercializing LLM-based applications involving prompt engineering, function calling, agentic workflows, or RAG.
- Experience designing and building large-scale distributed systems and real-time data-processing pipelines.
- Ability to make appropriate technical trade-offs in complex and rapidly changing environments.
- Strong ownership, problem-solving ability, and proactive execution skills.
- Strong verbal and written communication skills and experience collaborating with globally distributed teams.
- Preferred experience developing production agentic AI services with multi-agent frameworks such as LangGraph, CrewAI, or AutoGen.
- Preferred experience with vector databases such as Milvus, Pinecone, or Qdrant, as well as Kafka, EMR, S3, and AWS.
- Preferred experience with prompt engineering, LLM output evaluation, hallucination assessment, and automated evaluation infrastructure.
- Experience in high-volume domains such as large-scale e-commerce catalogs, search, recommendations, or advertising is preferred.
- Experience building testing infrastructure and CI/CD for microservice architectures is preferred.
- Experience delivering results in multicultural and cross-functional teams is preferred.
Benefits
- Full-time employment with a 12-week probationary period; the probation period may be waived, shortened, or extended when business needs require.
- The recruitment process includes document screening, role-fit interview, core competency interview, and final selection, subject to change by role and circumstances.
Categories
About Coupang
Coupang builds and operates a South Korea–focused e-commerce marketplace with an end-to-end logistics network (Rocket Delivery), plus food delivery, video streaming, and fintech under brands such as Coupang, Eats, and Play. Revenue comes from first-party retail, third-party marketplace services, advertising, and memberships (Rocket WOW). Founded in 2010, the company is headquartered in Seattle and is publicly listed on the NYSE (CPNG).