Machine Learning Engineer, CX Intelligence

Stack

Responsibilities

• ▹Architect multi-agent systems using advanced orchestration frameworks (LangGraph, Google ADK)
• ▹Build and scale integrations using Model Context Protocol (MCP) to connect LLMs with internal APIs and databases
• ▹Develop automated 'LLM-as-a-judge' evaluation pipelines to monitor non-deterministic AI agents in production
• ▹Implement RAG, fine-tuning, and prompt engineering to ensure grounded, compliant chatbot responses
• ▹Ship production-ready Python services that are resilient and low-latency
• ▹Partner with Conversation Design and Product to translate business logic into executable agent procedures

Requirements

• ▹3+ years building and scaling ML/AI systems in production, with agentic 'Loop' or 'ReAct' based systems
• ▹Deep understanding of the LLM lifecycle including context window management, token optimization, structured output parsing (Pydantic, JSON mode)
• ▹Strong Python proficiency with microservices architecture, asynchronous programming, high-throughput APIs, and vector databases (Pinecone, Weaviate)
• ▹Demonstrated ability to explain model behaviors and technical trade-offs to non-technical stakeholders

Soft skills

What we offer

• ▹Remote-first company with quarterly in-person 'surge' sessions
• ▹Equity and bonus eligibility
• ▹Medical, dental, and vision benefits

About the company

The CX Intelligence Engineering team is part of Coinbase's Enterprise Applications and Architecture org, building the multi-agent platform powering Coinbase Chat, Help Center, and agent tooling.