GCP GenAI/ Agentic AI Architect

PeopleNTech LLC

  • Santa Clara, CA
  • 30+ days ago
  • $100 Per Hour

Highlights

Experience working with Vector databases & design & deploy RAG pipelines, MCP Servers & A2A Implement robust LLMOPs - for continuous integration, deployment, monitoring, logging, and troubleshooting mechanisms for GenAI applications. Design & Implement Agentic AI systems using agent frameworks (AutoGen, LangGraph, CrewAI, etc.) to build multi-agent and goal-oriented systems.

Numbers & Facts

LocationSanta Clara, CA

Description

  • Bill Sell Rate: $100/hr.
  • Client Full Address: New Jersey
  • Remote / WFO / Hybrid: WFO
  • Hire Type (FTE/Contract): C2H
  • Project Duration: 8 Months, extendable
  • Expected Start Date: 8 Jul 26
  • Day 1 Billing Confirmation: Yes
  • No. of client interviews for this role: 1 to 2

We have an urgent requirement of GCPGenAI/ Agentic AI Architect for our customer, Everest Insurance.
Please find the required details, would request if you can share profiles quickly.
  • Indent ID: SF_OP_205306-1-1
  • Detailed JD:
Mandatory skills - Agentic AI Frameworks Langchain, LangGraph, CrewAI, VertexAI, Autogen etc.)
Good to have skills can be mentioned: Cloud Native, Microservice Architecture
  • 15+ years in software/solution architecture, proven experience as a Data Scientist or ML Engineer with exposure to agent-based AI systems.
  • Design & Implement Agentic AI systems using agent frameworks (AutoGen, LangGraph, CrewAI, etc.) to build multi-agent and goal-oriented systems.
  • Proficiency in Prompt Engineering, few-shot prompting, chain-of-thought reasoning, and prompt templates.
  • Familiarity with cloud-native AI platforms from AWS, Azure, or GCP (e.g., Bedrock, Azure OpenAI, Vertex AI).
  • Experience on AI for Engineering & working with AI Code Assist tools (e.g., Copilot, Windsurf, Cursor)
  • Experience working with Vector databases & design & deploy RAG pipelines, MCP Servers & A2A Implement robust LLMOPs - for continuous integration, deployment, monitoring, logging, and troubleshooting mechanisms for GenAI applications.
  • Develop and promote reusable architectural patterns, best practices, and governance frameworks for GenAI development.
  • Lead the end-to-end architectural design of Generative AI applications, ensuring scalability, performance, security, cost-effectiveness, and maintainability.
  • Proficiency in containerization technologies (Docker, Kubernetes) and CI/CD pipelines.
  • Must have experience working with Microservice architecture using Spring Boot Rest APIs & know API Security, Versioning
  • Must have experience designing CloudNative applications on any cloud such as AWS, Azure, GCP, Spring Cloud, PCF
  • Programming proficiency in Python (preferred), and optionally Java/Node.js for integration.
  • Collaborate with Data Scientists, Product Owners, and Business SMEs to translate business problems into AI-powered solutions.
  • Exceptional communication and presentation skills, with the ability to articulate complex technical concepts to both technical and non-technical audiences

Similar Jobs

See more jobs