한국어·English
Sendbird company · OPEN ROLE
- Company
- Connect customer memory with governed actions across channels.
- Role
- Own agent architecture, evaluations and delivery.
- Language
- Native-level English
Log in to mock apply, save this role or see more roles.
What you will do
We rewrote the responsibilities and qualifications in plain language instead of copying the original posting.
Responsibilities
- Owns end-to-end delivery of core AI agent features, from architecture through production.
- Designs and builds advanced RAG pipelines, multi-step tool use, and agent orchestration logic.
- Drives architecture decisions for the agent platform with a focus on fault tolerance and scalability.
- Builds and optimizes evaluation, observability, and classification pipelines that improve agent performance.
- Leads prompt engineering strategy for diverse customer cases, including A/B testing and regression pipelines.
- Guides junior engineers through code reviews, architecture discussions, and technical planning.
What you need
- Has 3+ years of software engineering experience owning AI/ML or backend systems in production.
- Has deep Python expertise and a track record of building and scaling reliable, performant systems.
- Has hands-on experience with LLM APIs.
- Has strong system design and architecture skills, including distributed systems on AWS or GCP.
- Has the English proficiency to communicate complex technical ideas clearly in writing and conversation.
Good to have
- Has prior experience with real-time or conversational interfaces.
- Has hands-on experience with agentic frameworks such as LangChain or LangGraph.
- Is familiar with vector databases, search technologies, or large-scale data processing.
Read the employer’s original job description
See how your resume reads for this role
A former Korea GM at a global company reads it and tells you what to improve for this role. It uses 1 credit.
Checked 2026-10-10
SendbirdSoftware Engineer, AI AgentStart a mock application