SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: BRL 347,900 - 347,900 / annual
The CX Intelligence Engineering team at Coinbase builds a multi-agent platform powering Coinbase Chat, Help Center, and agent tooling. As a Machine Learning Engineer, you'll design and scale agentic systems that automate complex customer support workflows, connecting large language models with internal APIs and tools to deliver fast, accurate, and compliant AI-powered experiences for millions of customers.
Key responsibilities include:
- Architect multi-agent systems using advanced orchestration frameworks (LangGraph, Google ADK) to automate complex customer support procedures end-to-end.
- Build and scale integrations using Model Context Protocol (MCP) to connect LLMs with internal Coinbase APIs, databases, and third-party tooling.
- Develop automated "LLM-as-a-judge" evaluation pipelines to monitor, measure, and improve the performance of non-deterministic AI agents in production.
- Implement RAG, fine-tuning, and prompt engineering techniques to ensure chatbot responses are grounded, accurate, and compliant with Coinbase policies.
- Ship production-ready Python services that are resilient, low-latency, and capable of handling Coinbase-scale traffic across asynchronous microservices.
- Partner with Conversation Design and Product teams to translate complex business logic into executable agent procedures.
Required qualifications:
- 3+ years building and scaling ML/AI systems in production, with demonstrated experience implementing agentic systems using Loop or ReAct-based architectures where AI takes actions autonomously.
- Deep understanding of the LLM lifecycle including context window management, token optimization, structured output parsing (Pydantic, JSON mode), and multi-agent orchestration frameworks.
- Strong proficiency in Python with hands-on experience in microservices architecture, asynchronous programming, high-throughput APIs, and vector databases (Pinecone, Weaviate, or equivalent).
- Demonstrated ability to explain model behaviors and technical trade-offs to non-technical stakeholders across CX, Legal, and Product teams.
- Ability to utilize generative AI responsibly, maintaining human oversight to deliver business-ready outputs and drive measurable improvements in workflow efficiency, cost, and quality.
Coinbase is a remote-first company with quarterly in-person working sessions called "surges."
