Posted time March 31, 2026 Location South Korea Job type Full-time

Job Description

We are looking for a highly experienced Senior Backend Engineer to design and build the core infrastructure powering our AI-driven travel discovery platform. In this role, you will develop high-performance backend systems that combine modern search technologies, vector databases, and large language model (LLM) architectures.

You will be responsible for building scalable systems capable of understanding traveler intent and delivering personalized travel experiences. This includes designing hybrid search systems, implementing AI-powered recommendation pipelines, and optimizing large-scale data retrieval systems.

As part of our engineering team, you will collaborate closely with product teams and AI engineers to develop advanced backend services that support real-time travel discovery, personalization, and intelligent travel assistance.


Key Responsibilities

  • Architect and develop hybrid search systems combining traditional search indexes and vector-based search technologies.
  • Build and optimize Retrieval-Augmented Generation (RAG) pipelines to power AI-driven travel discovery experiences.
  • Develop backend systems that integrate LLM-powered services with structured and unstructured data sources.
  • Implement graph-based personalization systems to connect users, destinations, attractions, and services.
  • Optimize embedding algorithms for transforming travel-related content into searchable vector representations.
  • Design and build high-performance APIs capable of handling high traffic and real-time queries.
  • Improve system performance by optimizing latency, caching strategies, and scalability.
  • Collaborate with cross-functional teams to design scalable backend architectures for AI-driven products.

Technical Skills Required

  • 5+ years of experience in backend development using Go, Java, Python, or Node.js.
  • Strong knowledge of search technologies such as Elasticsearch, Solr, or Lucene-based systems.
  • Experience with vector databases such as Milvus, Pinecone, Weaviate, or similar technologies.
  • Familiarity with LLM architectures and AI-powered search workflows (RAG pipelines).
  • Experience working with graph databases like Neo4j or ArangoDB.
  • Strong understanding of API architecture, microservices, and distributed systems.
  • Knowledge of data indexing, query optimization, and high-performance backend systems.
  • Experience with cloud platforms (AWS, GCP, or similar).
  • Familiarity with containerization and modern backend infrastructure.

Hiring Process

  1. Application Submission – Submit your resume through our career page.
  2. Initial Screening – HR team reviews your experience and background.
  3. Technical Interview – Discussion focused on backend architecture, search technologies, and AI infrastructure.
  4. Technical Assessment (Optional) – Candidates may complete a short architecture or coding task.
  5. Final Interview – Meeting with the engineering leadership team.
  6. Offer & Onboarding – Selected candidates will receive an offer and onboarding details.

Work Location

Seoul, South Korea (Gangnam / Pangyo) – Remote Friendly

Candidates can work remotely while collaborating with our international engineering team.