Senior AI Architect

Role: Senior AI Architect

Location: Sunnyvale, VA(Local candidates preferred)

Interview: In-person

Duration: 1 year's contract

Role Overview

The Senior AI Architect & Lead Prompt Engineer will spearhead the design and deployment

of advanced, next-generation agentic systems and LLM-powered platforms for GFiber. This

pivotal role necessitates the integration of sophisticated Prompt Engineering and AI

Architecture principles with scalable AI infrastructure to optimize GFiber's enterprise workflows.

Leveraging a background in the Telecommunications sector, the incumbent will integrate AI

agents with core enterprise platforms, including but not limited to ServiceNow, Salesforce,

Netcracker, and SAP, to automate complex customer inquiry cycles and enhance on-field

employee support. This integration is designed to yield substantial reductions in Capex and

Opex, ensure end-to-end service management for both internal and external GFiber

stakeholders, and involve the creation of reusable AI assets and the cultivation of mentorship

capabilities.

Key Responsibilities

● AI Architecture & Design: Lead the end-to-end architecture of multi-agent

systems, moving from initial concept to production-grade deployment on Google

Cloud Platform (GCP).

● Prompt Engineering & Orchestration: Develop sophisticated prompt

engineering frameworks, including system prompts, few-shot templates, and

output guardrails. Utilize Chain-of-Thought (CoT) prompting and structured

prompt chains for complex reasoning tasks.

● Intelligent Dialog Systems: Design conversational interfaces using Dialogflow

and Gemini-powered agents to manage inquiry routing and automated workflow

orchestration.

● System Integration: Architect integrations between LLM platforms (Vertex

AI/Gemini) and enterprise CRM/ITSM tools like Salesforce and ServiceNow,

specifically focusing on Telecom-grade inquiry response and ticketing workflows.

● RAG & Knowledge Retrieval: Build and optimize RAG (Retrieval-Augmented

Generation) pipelines grounded in internal client policies and technical

documentation.

● MLOps & Deployment: Oversee the deployment of microservices using GKE

(Google Kubernetes Engine), Cloud SQL, and Cloud Build, ensuring scalable

and reliable AI performance.

Required Core Expertise

● LLM Stack: Deep expertise in Gemini, Vertex AI, and LangChain or

LlamaIndex.

● Enterprise Integration: Proven experience architecting AI solutions that

interface with Salesforce and ServiceNow within a Telecom or large enterprise

context.

● Agentic Systems: Experience building multi-agent architectures for autonomous

task execution and workflow automation.

● Data & Search: Mastery of hybrid search, reranking, and vector databases (e.g.,

Redis, PostgreSQL).

Qualifications

● Experience: 10 years in the AI stack, ranging from classical NLP/NLU to

modern generative AI architectures.

● Education: B.Tech in Computer Science, Mathematics, or a related technical

field.

● Technical Proficiency: Strong command of Python, Terraform IAC, Docker, and

the GCP ecosystem (GKE, Cloud Deploy).

● Industry Knowledge: Demonstrated understanding of the Service Now,

Salesforce, Net Cracker in Telecommunications service lifecycle, specifically

regarding inquiry management and automated support.

Tools & Platforms

● AI/ML: Gemini, Vertex AI, Hugging Face, OpenAI, Claude.

● Frameworks: LangChain, LlamaIndex, Dialogflow.

● Cloud & Infra: GCP (GKE, Cloud Build), Docker, TensorRT.

● Data: Cloud SQL, PostgreSQL, Redis.