GenAI Forward Deployed Engineer (FDE)

External job listingat Valzosoft

Tasks Build and deploy production-grade GenAI and Agentic AI solutions, including multi-agent workflows and MCP servers. Develop integrations between Google Cloud AI, Gemini, Dialogflow C...

External source - not verified17 hours agoOpen until: Jan 25, 2027

Salary

Not provided

Location

San Jose, United States

Employment type

Full time

Workplace

Not provided

GenAI Forward Deployed Engineer (FDE)

San Jose, United States

Job description

Tasks

  • Build and deploy production-grade GenAI and Agentic AI solutions, including multi-agent workflows and MCP servers.
  • Develop integrations between Google Cloud AI, Gemini, Dialogflow CX, Customer Engagement Suite (CES), and Contact Center AI (CCAI) and enterprise systems.
  • Build scalable RAG pipelines, vector database integrations, and structured/unstructured data workflows.
  • Develop AI evaluation pipelines, observability frameworks, and tracing mechanisms to improve accuracy, safety, latency, and cost.
  • Lead customer-facing technical discovery sessions and collaborate directly with customer engineering teams.
  • Convert real-world implementation challenges into reusable components and product improvement recommendations.

Requirements

  • 5+ years of hands-on software development experience using Python
  • Google Cloud Platform (GCP) and cloud-based AI architecture
  • Generative AI, LLMs, RAG, and Vector Databases
  • Production deployment of AI-driven enterprise solutions
  • Google Conversational AI: Dialogflow CX, Gemini-powered CX, CES, and CCAI
  • Customer-facing technical discovery and solution implementation
  • API integrations, enterprise data pipelines, and security integration
  • Preferred: Experience with LangGraph, CrewAI, Google ADK, and multi-agent frameworks
  • Preferred: Knowledge of MCP servers, ReAct, self-reflection, and hierarchical agent delegation
  • Preferred: Experience with voice AI, Agent Assist, CX Agent Studio, and CCaaS
  • Preferred: Understanding of LLM observability, token usage, latency optimization, and cost-per-reques

Location

  • San Jose, CA

Similar jobs