Machine Learning Engineer, CX Intelligence

Overview

You will build and scale agentic machine learning systems for automated customer support workflows within Coinbase’s CX Intelligence Engineering team.

What you'll do

• Architect multi-agent systems for end-to-end customer support automation using orchestration frameworks.
• Build and scale integrations connecting LLMs with internal APIs, databases, and third-party tooling.
• Develop evaluation pipelines to monitor, measure, and improve production performance of AI agents.
• Implement RAG, fine-tuning, and prompt engineering approaches for grounded, accurate, compliant responses.
• Ship production-ready Python services designed for resilience and low latency across microservices.
• Partner with Conversation Design and Product to translate logic into executable agent procedures.

What you'll need

• 3+ years building and scaling ML/AI systems in production.
• Experience implementing agentic “Loop” or “ReAct” based systems with autonomous actions.
• Deep understanding of the LLM lifecycle including context window management and token optimization.
• Strong Python skills with experience in microservices, asynchronous programming, and high-throughput APIs.
• Experience with vector databases such as Pinecone or Weaviate.
• Ability to explain model behaviors and technical trade-offs to non-technical stakeholders.

Details

• Location: Remote - Brazil.