Coinbase은/는 Engineering Manager를 채용합니다. 생성형 AI를 활용한 고객 지원 플랫폼을 구축하며, LLM, RAG, Golang 기술 스택을 다룹니다. 8년 이상의 소프트웨어 개발 경력과 2년 이상의 리딩 경험이 필수입니다. 분산 시스템 설계 및 AI 평가 프레임워크 구축 역량이 중요합니다.
Ready to do the most impactful work of your career? At Coinbase, we are uncompromising on our mission to increase economic freedom. The bar is high, the environment is intense, and we like it that way. This isn't a place for complacency, it’s a place to be pushed past your perceived limits. If you're ready to build the future of finance alongside people who refuse to settle for "good enough," you belong here. Coinbase is a remote-first, but not remote-only company. Expect to get together quarterly for intense in-person working sessions called “surges.” learn more about working at Coinbase.
The CXAI Engineering team sits within Coinbase’s Consumer Engagement and Experience (CEE) organization and is reimagining crypto support through generative AI. We build systems that help customers get fast, accurate, and secure resolutions by combining intelligent orchestration, trusted context retrieval, and action across blockchain and app surfaces.
We’re hiring an Engineering Manager to lead development of our AI-powered Automated Resolution platform. You will guide a team building across internal LLM-based agents and key third-party integrations, shaping the intelligence layer that understands complex issues, retrieves the right context, and takes meaningful action.
Drive the roadmap for our conversational AI platform, advancing from decision trees to LLM reasoning, RAG, and agentic workflows.
Lead integration of third-party AI solutions while scaling in-house LLM infrastructure for high-stakes crypto support.
Build evaluation frameworks and feedback loops to improve model accuracy, grounding, compliance, and customer outcomes.
Enable secure agent actions for workflows such as transaction troubleshooting and account recovery through internal APIs.
Define technical architecture across vector databases, prompt design, and context management to deliver personalized support.
Own operational excellence across reliability, latency, token cost, and fallback paths to human agents.
8+ years of software engineering experience, including 2+ years leading high-performing teams.
Experience shipping products powered by large language models, with strong understanding of prompt engineering, fine-tuning, and the model provider landscape.
Experience building RAG pipelines and managing the data lifecycle needed to ground AI in real-time knowledge.
Strong systems and platform background, including scalable distributed systems in high-traffic production environments.
Experience designing quantitative AI evaluation frameworks to measure hallucination rates, accuracy, and customer sentiment.
Deep understanding of AI safety and guardrails, including preventing PII leakage and unsafe financial outputs.
Familiarity with vector databases such as Pinecone, Weaviate, or Milvus, and orchestration frameworks such as LangChain or LlamaIndex.
Proficiency in Golang and experience with modern cloud-native infrastructure such as AWS and Kubernetes.
Utilizes generative AI responsibly, maintaining human oversight to deliver business-ready outputs and drive measurable improvements in workflow efficiency, cost, and quality
Job ID - P75782
Pay Transparency Notice: The target annual base salary for this position can range as detailed below. Total compensation may also include equity and bonus eligibility and benefits (including medical, dental, and vision).
Annual base salary range (excluding equity and bonus):
₹9,424,500—₹9,424,500 INR
