Gen AI Forward Deployed Engineer

ZENITH INFOTEK LLC; United States; Remote; USD 150,000 - 210,000; Full time

Job summary

Zenith Infotek LLC seeks a highly hands-on GenAI Forward Deployed Engineer (FDE) to build and deploy production-grade AI solutions for enterprise customers.

You will design, code, integrate, debug, deploy, and optimize sophisticated agentic AI applications directly with customer engineering teams, bridging Google Cloud AI products with real-world environments. This remote role requires a strong software/cloud background and the ability to drive engagements end-to-end.

Qualifications

• Bachelor’s degree in CS/engineering or equivalent.
• 5+ years of professional software development.
• Experience deploying AI/ML on cloud platforms.
• Hands-on with enterprise GenAI and multi-agent systems.
• Strong ability to run technical discovery sessions with customers.

Responsibilities

• Build and deploy complex GenAI and agentic AI applications, moving solutions from prototypes to production.
• Develop multi-agent workflows, MCP servers, RAG architectures, and enterprise AI applications that deliver measurable business value.
• Architect and implement integrations between Google Cloud AI products and customer environments, including APIs, legacy systems, enterprise data sources, and security boundaries.
• Work with technologies across the Google Enterprise CX ecosystem, including Gemini, Conversational Agents, CES, and CCAI.
• Build data pipelines for structured and unstructured enterprise data, including vector databases and RAG-based architectures.
• Develop evaluation frameworks and observability solutions to measure accuracy, safety, latency, cost, and overall agent performance.
• Troubleshoot production blockers involving data readiness, integrations, authentication, state management, security, and system performance.
• Lead technical discovery sessions with customer engineering and business stakeholders.
• Collaborate directly with customer teams to design, implement, test, and productionize AI solutions.
• Identify recurring implementation challenges and convert field learnings into reusable components, accelerators, or product feedback for engineering teams.
• Establish engineering best practices and help customer teams successfully maintain and scale deployed solutions.
• Independently drive execution on complex customer engagements while mentoring and upskilling partner engineering teams.

Skills

Python

GenAI

Cloud architecture

GCP

RAG architectures

Vector databases

LLM/GenAI

Production deployments

Dialogflow CX

CCAI

Education

Bachelor’s degree in CS/Engineering

Tools

LangGraph

CrewAI

Google ADK

Dialogflow CX

CX Agent Studio

Agent Assist

CCAI

Job description

GenAI Forward Deployed Engineer (FDE)

Location: Remote
Work Hours: PST
Employment Type: Contract / Full-Time

Job Title: GenAI Forward Deployed Engineer (FDE)
Location: Remote
Work Hours: PST

Duration: 8+ Months (Contract)
Interview: Video Interview

Job Summary

We are seeking a highly hands‑on GenAI Forward Deployed Engineer (FDE) to build and deploy production‑grade AI solutions for enterprise customers.

The FDE acts as an innovator‑builder, bridging the gap between advanced Google Cloud AI products and real‑world enterprise environments. This role goes beyond advisory architecture—you will design, code, integrate, debug, deploy, and optimize sophisticated agentic AI applications directly with customer engineering teams.

The ideal candidate is a high‑agency engineer with strong software development skills, cloud architecture expertise, enterprise AI experience, and the ability to independently drive complex technical engagements from discovery through production.

Key Responsibilities

• Build and deploy complex GenAI and agentic AI applications, moving solutions from prototypes to production.
• Develop multi-agent workflows, MCP servers, RAG architectures, and enterprise AI applications that deliver measurable business value.
• Architect and implement integrations between Google Cloud AI products and customer environments, including APIs, legacy systems, enterprise data sources, and security boundaries.
• Work with technologies across the Google Enterprise CX ecosystem, including Gemini, Conversational Agents, Customer Engagement Suite (CES), and Contact Center AI (CCAI).
• Build data pipelines for structured and unstructured enterprise data, including vector databases and RAG-based architectures.
• Develop evaluation frameworks and observability solutions to measure accuracy, safety, latency, cost, and overall agent performance.
• Troubleshoot production blockers involving data readiness, integrations, authentication, state management, security, and system performance.
• Lead technical discovery sessions with customer engineering and business stakeholders.
• Collaborate directly with customer teams to design, implement, test, and productionize AI solutions.
• Identify recurring implementation challenges and convert field learnings into reusable components, accelerators, or product feedback for engineering teams.
• Establish engineering best practices and help customer teams successfully maintain and scale deployed solutions.
• Independently drive execution on complex customer engagements while mentoring and upskilling partner engineering teams.

Minimum Qualifications

• Bachelor’s degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience.
• 5+ years of professional software development experience, preferably with Python or similar programming languages.
• Strong experience architecting and deploying AI/ML systems on cloud platforms, preferably GCP.
• Hands‑on experience building enterprise AI solutions using:
  
  • RAG architectures
• • Vector databases
• • Structured and unstructured data pipelines
• • LLM/GenAI applications
• Proven experience taking production‑grade AI solutions from concept through deployment and launch.
• Experience conducting technical discovery sessions and working directly with enterprise customers.
• Hands‑on implementation and customization experience with Google's conversational AI ecosystem, including:
  
  • Dialogflow / Conversational Agents
• • Gemini‑powered CX
• • Customer Engagement Suite (CES)
• • Contact Center AI (CCAI)

Preferred Qualifications

• Master’s or PhD in Computer Science, Artificial Intelligence, Machine Learning, or a related technical discipline.
• Experience building multi‑agent systems using frameworks such as:
  
  • LangGraph
• • CrewAI
• • Google ADK
• Experience implementing advanced agentic patterns such as:
  
  • ReAct
• • Self‑reflection
• • Hierarchical delegation
• • Multi‑agent orchestration
• Strong understanding of LLM‑native performance metrics, including:
  
  • Tokens per second
• • Cost per request
• • Latency
• • Model utilization
• • Agent accuracy
• Experience with state management, tracing, evaluation, and observability for agentic systems.
• Experience with production‑grade conversational and voice AI systems across:
  
  • Dialogflow CX
• • CX Agent Studio
• • Agent Assist
• • CCAI / CCaaS
• • SCRAPI
• Strong understanding of enterprise authentication, APIs, security architecture, and integration patterns.
• Experience working with telecommunications APIs and enterprise telecom architectures.
• Ability to operate as a senior tiger‑team engineer, independently solving ambiguous and technically complex problems.
• Experience mentoring and enabling customer or partner engineering teams.

This is a remote position.