Jobiglo

Sem resultados

Machine Learning Engineer, CX Intelligence

Coinbase · Remote - Brazil

Novo Remote
Remote Senior 347,900 BRL/ano 🇬🇧 English
Python LangGraph Google ADK Model Context Protocol RAG Fine-tuning Pydantic Microservices Asynchronous programming Vector databases Pinecone Weaviate

Descrição do cargo

About the role

Coinbase's CX Intelligence Engineering team, part of the Enterprise Applications and Architecture organization, builds the multi-agent platform behind Coinbase Chat, the Help Center and agent tooling. As a Machine Learning Engineer you will design and scale agentic systems that automate complex customer support workflows by connecting LLMs with internal APIs and tools, delivering fast, accurate and compliant AI experiences for millions of customers. The company is remote-first but expects quarterly in-person working sessions.

Key responsibilities

  • Architect multi-agent systems using orchestration frameworks such as LangGraph and Google ADK to automate customer support procedures end-to-end.
  • Build and scale integrations via the Model Context Protocol (MCP) that connect LLMs with internal APIs, databases and third-party tooling.
  • Develop automated "LLM-as-a-judge" evaluation pipelines to monitor and improve the performance of non-deterministic AI agents in production.
  • Apply RAG, fine-tuning and prompt engineering so chatbot responses are grounded, accurate and compliant with Coinbase policies.
  • Ship production-ready Python services that are resilient, low-latency and able to handle Coinbase-scale traffic across asynchronous microservices.
  • Work with Conversation Design and Product to turn complex business logic into executable agent procedures.

Required profile

  • 3+ years building and scaling ML/AI systems in production, including agentic "Loop" or "ReAct" systems where AI acts autonomously.
  • Ability to explain model behavior and technical trade-offs to non-technical stakeholders across CX, Legal and Product teams.
  • Uses generative AI responsibly, keeping human oversight and driving measurable improvements in workflow efficiency, cost and quality.

Required skills

  • Deep understanding of the LLM lifecycle, context window management, token optimization, structured output parsing (Pydantic, JSON mode) and multi-agent orchestration frameworks.
  • Strong Python, microservices architecture, asynchronous programming, high-throughput APIs and vector databases (Pinecone, Weaviate or equivalent).

Questions fréquentes

Le salaire proposé pour ce poste est de 348k BRL par an. Le détail figure dans l'annonce.
Cliquez sur "Postuler maintenant" en haut de la page. Vous pouvez importer votre CV en 1 clic — Jobiglo extrait automatiquement vos informations et postule pour vous.
Source : ats:greenhouse

Motivo do reporte

Obrigado! A sua denúncia foi enviada aos administradores.

Candidate‑se em 30 segundos

Introduza o seu e‑mail para candidatar‑se. Uma conta será criada automaticamente.

Candidatar-se agora →

Ao continuar, aceita os nossos termos de uso.

Já tem uma conta? Entrar

Uma pergunta sobre esta oferta?

Faça-a aqui: receberá o resumo completo por e-mail, de imediato.

Publicado há 1 dia

Expira em 1 mês

6 visualizações · 0 interested

Aumente suas chances

Envie seu CV: vamos sugerir as vagas que combinam com seu perfil.

A analisar o seu CV...

Coinbase

Remote - Brazil