Forward Deployed Engineer, Gen Ai, Google Cloud Consulting (portuguese, Spanish, English)

Google Google · Big Tech · São Paulo, State of São Paulo, Brazil +1

Forward Deployed Engineer building and shipping agentic AI solutions within customer environments on Google Cloud, focusing on integration, data readiness, and state management. Responsibilities include developing agentic workflows, architecting connective tissue, building evaluation and observability pipelines, and providing feedback for product roadmap. Requires software development, cloud consulting, and experience with RAG/vector databases. Fluency in Portuguese, Spanish, and English is essential.

What you'd actually do

  1. Serve as a developer for complex AI applications, transitioning from rapid prototypes to production-grade agentic workflows (e.g., multi-agent systems, model context protocol (MCP) servers) that drive measurable return on investment (ROI).
  2. Architect and code the connective tissue between Google’s AI products and customer's live infrastructure, including application programming interface (APIs), legacy data silos, and security perimeters as part of an expert team.
  3. Build high-performance evaluation pipelines and observability frameworks to ensure agentic systems meet rigorous requirements for accuracy, safety, and latency.
  4. Identify repeatable field patterns and friction points in Google’s AI stack, converting them into reusable modules or formal product feature requests for engineering teams. Be able to co-build with customer engineering teams to instill Google-grade development best practices, ensuring long-term project success and high end-user adoption.

Skills

Required

  • Python
  • Cloud Consulting
  • architecting AI systems on cloud platforms
  • building pipelines for structured and unstructured data
  • vector databases
  • Retrieval-Augmented Generation (RAG)-like architectures
  • Portuguese
  • Spanish
  • English

Nice to have

  • Master’s degree or PhD in AI, Computer Science, or a related technical field
  • leading technical discovery sessions
  • implementing multi-agent systems using frameworks (e.g., LangGraph, CrewAI, agent development kit (ADK))
  • complex patterns (e.g., ReAct, self-reflection, hierarchical delegation)
  • Large Language Models (LLM)-native metrics (e.g., tokens/sec, cost-per-request)
  • optimizing state management
  • granular tracing

What the JD emphasized

  • production-grade agentic workflows
  • customer's live infrastructure
  • high-performance evaluation pipelines
  • observability frameworks
  • agentic systems meet rigorous requirements

Other signals

  • building agentic solutions
  • production-grade AI
  • customer integration