이 공고, 이렇게 물어볼 겁니다

AI 에이전트 플랫폼의 아키텍처를 설계할 때, 시스템의 확장성(Scalability)과 장애 허용성(Fault Tolerance)을 확보하기 위해 구체적으로 어떤 분산 시스템 패턴(예: Agent Orchestration, RAG Pipeline)을 선택했으며, 그 결정이 실제 서비스 지연 시간(Latency)과 비용에 어떤 영향을 미쳤는지 숫자로 설명해 주십시오.

🎯 시스템 설계의 깊이와 실제 운영 환경에서의 트레이드오프(Trade-off) 이해도를 확인

RAG 파이프라인 성능을 개선하기 위해 임베딩 모델이나 검색 로직을 개선했던 경험 중, 단순히 성능 지표(예: Recall, MRR)를 높이는 것을 넘어, 실제 사용자 경험(Delight) 개선에 기여한 구체적인 사례와 그 결과를 설명해 주십시오.

🎯 기술적 개선이 비즈니스 가치로 이어지는 End-to-End 기여도를 확인

LLM 기반 기능을 프로덕션에 배포하는 과정에서, 프롬프트 엔지니어링 전략과 시스템 아키텍처 중 어디에 더 큰 비중을 두어야 한다고 생각하며, 그 경계를 설정한 구체적인 의사결정 사례를 제시해 주십시오.

🎯 AI 개발에 대한 기술적 철학과 전략적 사고를 확인

운영 중 시스템이 중대한 오류를 일으켰을 때, 그 원인을 파악하고 재발 방지책을 마련했던 가장 복잡한 경험을 설명해 주십시오. 특히, AI 에이전트의 비결정론적(Non-deterministic) 행동을 어떻게 디버깅하고 안정화했는지 과정과 해결책을 구체적인 로그 및 측정 지표를 중심으로 설명해 주십시오.

🎯 문제 해결 능력, 디버깅 능력, 그리고 AI 시스템의 특성을 이해하는지 확인

주니어 엔지니어들을 멘토링할 때, 단순히 코딩 방법론을 가르치는 것을 넘어, AI-Native 개발 표준과 시스템 사고방식을 어떻게 교육하고 심어주었는지 구체적인 멘토링 사례와 그들이 주도한 프로젝트의 성과를 들어 설명해 주십시오.

🎯 리더십, 코칭 능력, 그리고 조직 내 기술 표준을 확립하는 능력을 확인

질문만 읽으면 컨닝이에요. 소리 내어 답해보세요 — 어디서 틀어지는지 짚어드립니다.

공고 내용

The Company

Sendbird is on a mission to build the AI workforce of tomorrow. For over a decade, we built the infrastructure behind conversations—chat, voice, video, messaging APIs—and became the #1 CPaaS platform for in-app communications. 4,000+ brands trust us. 7 billion messages flow through our platform every month. 300 million monthly active users.

We powered conversations for DoorDash, Match Group, Noom, Yahoo Sports, Rakuten, and thousands of others. We were good at what we did. Really good.

We also saw it early: AI would fundamentally reshape how businesses talk to customers. The infrastructure we'd spent a decade building would become commoditized. The value would move up the stack—into intelligence, into experience, into outcomes.

We had a choice: protect what we built, or reinvent ourselves.

We chose reinvention.

In December 2024, we made the full strategic pivot to AI-first customer experience. By February 2025, we'd launched our AI agent for enterprise CX—built on a decade of conversation data, now with intelligence on top. And in November 2025, we rebranded to Delight.ai.

The name says it all. AI's real promise isn't efficiency or cost savings. It's giving customers back something they lost—the feeling of being truly understood and cared for. Not satisfied. Delighted.

The Product

Delight.ai is the AI concierge for customer experience. Most AI agents forget you the moment the conversation ends. Ours doesn't. Delight.ai builds memory over time, learns preferences, and connects context across every channel—chat, SMS, email, voice, WhatsApp—without losing the thread. We're building AI that makes customers feel understood, seen, and remembered.

The Role

You'll own end-to-end delivery of core AI agent capabilities, from architecture to production, driving excellence across orchestration, prompt engineering, and platform scalability. You'll mentor the engineers around you and set the standard for AI-native development. This role is built for someone who moves fast, thinks in systems, and uses AI to ship at a pace that surprises people.

You might be this person if:

· You've owned a system that broke in production, made it better, and still think about why it broke.

· You use agentic tools like Claude Code or Codex as a core part of your dev workflow, not as a novelty.

· You enjoy mentoring junior engineers not because it's expected, but because you genuinely care about how they grow.

· You've shipped LLM-powered features into production and have strong views on where prompt engineering ends and architecture begins.

· You've led technical planning in a cross-functional setting and can hold your own in a room with PMs, designers, and engineers at once.

You need to have:

· 3+ years of software engineering experience with direct ownership of AI/ML or backend systems in production.

· Deep Python expertise with a proven track record of building and scaling reliable, performant systems.

· Hands-on experience with LLM APIs.

· Strong system design and architecture skills, including distributed systems and cloud-native deployments on AWS or GCP.

· Strong English proficiency. You can communicate complex technical ideas clearly in writing and in conversation.

What you'll actually do:

· Design and implement core agent features including advanced RAG pipelines, multi-step tool use, and agent orchestration logic.

· Drive architectural decisions for the AI agent platform with a focus on fault tolerance, scalability, and extensibility.

· Build and optimize evaluation, observability, and classification pipelines that improve agent performance over time.

· Lead prompt engineering strategy for diverse customer use cases, including designing A/B testing and automated regression pipelines.

· Improve retrieval logic and embedding models to push RAG pipeline performance further.

· Monitor AI research and actively bring relevant techniques into production systems, using agentic CLIs and automation tooling to accelerate iteration cycles.

· Guide junior engineers and interns through code reviews, architectural discussions, and technical planning.

· Partner with PMs, designers, and sales engineers to translate real customer needs into well-scoped technical solutions.

Added Value:

· Prior experience with real-time or conversational interfaces.

· Hands-on experience with agentic frameworks such as LangChain or LangGraph.

· Familiarity with vector databases, search technologies, or large-scale data processing.

· Contributions to open-source LLM or AI tooling ecosystems.

· Native-level English fluency.

Our KR benefits include (but are not limited to):

· Silicon Valley's equity program (1-year cliff)

· Hybrid work policy, flexible work hours

· Be Your Best Self: 3.9 million won (prorated by start date) for expenses ranging from professional development classes and training, to personality assessments, to gym memberships, to books, to fitness classes, to mental health services, to massages

· Learn a Language benefit - up to 3.6 million

원문에서 전체 공고 보기 →