AI Agent PM

About the role

| 이런 경험을 할 수 있어요
• Real-world LLM Alignment: Gain rare, hands-on experience orchestrating customer-facing AI Agents that handle live customer traffic, optimizing alignment through continuous feedback loops.
• AI-Native Workflow Mastery: Immerse yourself in a culture that leverages AI across the board - from ideation and engineering to data analysis and documentation - making AI fluency a core part of how you work.
• Global AI Product Leadership: Build your career as a Global AI Product Manager by leading the End-to-End Product Lifecycle (Planning, Deployment, Operation, Improvement) based on user data from diverse languages and cultures.
• Data-Driven Decision Making: Develop the capability to derive quantitative Product Insights by analyzing hundreds of thousands of actual customer conversation logs using AI.
• Global Cross-Functional Leadership: Strengthen your leadership by collaborating with diverse functional organizations (Knowledge Management, CS Operations, Platform, Data Teams) and global stakeholders.


| 이런 도구와 기술을 활용하고 있어요
Our team works hands-on with Frontier Models and modern SaaS tools daily.
• LLM/MLLM: Almost Frontier Models (GPT, Claude, Gemini, Qwen, etc.)
• Cloud Platforms: Azure, AWS, Google Cloud (including AI/ML managed services)
• Data Solutions: Snowflake, BigQuery/BigLake, Firestore, Cosmos DB
• Collaboration & Productivity: Jira, Slack, Confluence (w/ Atlassian Rovo), Google Workspace (w/ Gemini Pro, NotebookLM Pro), Claude Code
• SaaS Integrations: Salesforce, Sendbird, Lokalise

What you'll do

| 우리는 이런 일을 해요
1. Product Roadmap & Alignment
• Strategic Alignment: Coordinate with Game Product, Engineering, and Operations teams prior to new feature launches or system changes to ensure the Agent is aligned with the latest Context.
• Roadmap Execution: Define the Product Roadmap to achieve key metrics (e.g., Deflection Rate, CSAT) and coordinate release schedules with development teams.
• Market & Technology Intelligence: Conduct competitive analysis on CS AI solutions and emerging LLM capabilities to inform the product strategy.

2. Agent Ops & Quality Control
• Continuous Monitoring: Monitor Agent responses in real-time to detect hallucinations and inappropriate answers. Resolve issues through Prompt/Instruction Tuning or by escalating to the appropriate teams.
• Edge Case & Safety Management: Identify unexpected user scenarios, adversarial inputs (e.g., jailbreaking attempts), and policy violations. Evaluate and strengthen safety guardrails to ensure the Agent handles unforeseen situations gracefully.
• Performance Optimization: Collaborate cross-functionally with Knowledge Base, CS Ops, Contents, and Data Teams to update Grounding Resources and address root causes of performance issues.
• Evaluation Management: Build and maintain curated evaluation sets (Golden Test Sets) covering typical user queries and edge cases. Continuously track metrics (Accuracy, Relevance, Groundedness) to ensure response consistency.

3. Data-Driven Insight & Risk Management
• Anomaly Detection: Detect sudden changes in User Query Patterns to identify potential system failures or bugs, promptly escalating them to Operation/Engineering teams.
• VOC Analysis: Surface Voice of Customer data from conversation logs to provide actionable insights that drive Product Improvement across the entire organization.

Requirements

| 이런 분과 함께 하고 싶어요
• Total Experience: 7+ years (with 5+ years in PM/PO roles)
• Business-Fluent English (Verbal & Written): Ability to discern subtle nuance and context in English text and apply that precision to Prompt Engineering - beyond conversational fluency.
• Hybrid Role Capability: Ability to balance the strategic planning ("Why") of a Product Owner with the execution and management ("How") of a Project Manager.
• Analytical Problem Solving: Ability to logically decompose complex issues and derive solutions based on Data.
• Technical Understanding: Working understanding of LLM Core/Application mechanisms (Token, Temperature, Context Window, CoT, Extended Thinking, Tool Calling, Grounding) and Prompt Engineering techniques.

Preferred qualifications

| 이런 경험이 있으면 더 좋아요
• Experience or understanding of the iGaming or Regulated Business.
• Personal interest in Poker, iGaming or game theory - helpful for building empathy with our core user persona.
• Understanding of the Customer Support Domain or experience with CS System projects.
• Experience in planning, commercializing, and operating LLM-based Conversational AI services.
• Experience building or prototyping products using Agentic Coding tools (e.g., Claude Code, Antigravity, GitHub Copilot, Cursor).
• Experience with the Salesforce Ecosystem and data analysis skills using Python/SQL.

Benefits

| 앤서스랩코리아가 더 궁금하다면?
• 앤서스랩코리아 최신 소식 보러가기: https://nsuslab.com/#/departments
• ATI팀 소개 바로 가기: https://nsuslab.com/#/departments/ati

| 근무 형태 및 시간
• 근무 형태 : 정규직 (시용 3개월 종료 후, 정규직 전환 가능 대상 / 정규직 급여와 동일)
• 근무 시간 : 선택적 근무제 (출근시간 : 오전 9시 ~ 11시)

Hiring process

| 이런 여정을 거쳐 합류해요
영어 역량 검사(PC 환경)＞Culture Fit(전화인터뷰)&직무 적합성 검사＞실무 면접＞평판 조회＞처우 협의＞최종 합격
*자세한 채용 절차 및 FAQ는 링크(https://nsuslab.com/#/road-to-nsus)를 통해 확인해 주세요