Machine Learning Engineer, CX Intelligence

📋 Description

• Architect multi-agent systems with LangGraph and ADK to automate CX workflows.
• Build and scale MCP-based integrations connecting LLMs with Coinbase APIs and databases.
• Develop automated LLM-as-a-judge evaluation pipelines to monitor AI agents in production.
• Implement RAG, fine-tuning, and prompt engineering for grounded, compliant responses.
• Ship production-grade Python services, resilient and low-latency for Coinbase-scale traffic.
• Partner with Conversation Design and Product to translate business logic into agent procedures.

🎯 Requirements

• 3+ years building and scaling production ML/AI systems with autonomous agent loops.
• Deep understanding of the LLM lifecycle: context windows, token optimization, JSON/Pydantic, and multi-agent frameworks like LangGraph/ADK.
• Strong Python, microservices, async programming, high-throughput APIs, and vector DBs (Pinecone, Weaviate).
• Able to explain model behaviors and trade-offs to CX, Legal, and Product stakeholders.
• Demonstrates responsible AI use with human oversight to improve workflow efficiency, cost, and quality.

🎁 Benefits

• Equal Opportunity Employer; Coinbase is an Equal Opportunity Employer.
• Accommodations available; email accommodations@coinbase.com.
• Remote-first culture with quarterly in-person surges.