Agentic AI Architect with Google Vertex AI
Agentic AI Architect with Google Vertex AI
Posted on :
25-06-2025
Employer Active
1 Vacancy
Job Alert
You will be updated with latest job alerts via emailValid email field required
Send jobs
Share
Send me jobs like this
Job Alert
You will be updated with latest job alerts via emailValid email field required
Send jobs
Monthly Salary
Not Disclosed
Salary Not Disclosed
Vacancy
1 Vacancy
Posted on :
25-06-2025
Job Description
Strictly Local Candidates - Detroit/ MI
We are seeking a highly skilled Agentic AI Architect to lead the design and development of sophisticated AI agent systems using Google Cloud Platforms Vertex AI suite. This hands-on role requires deep expertise in building autonomous AI systems that can reason plan and execute complex tasks using large language models and advanced orchestration frameworks.
Key Responsibilities
Design and implement agentic AI architectures using Google Vertex AI models (Gemini PaLM Codey)
Develop and deploy AI agents using LangChain and Model Context Protocol (MCP) architectures
Build scalable production-ready AI systems leveraging GCP services including Vertex AI Pipelines Matching Engine and AI Platform
Implement multi-agent systems with complex reasoning planning and tool-use capabilities
Design and optimize vector databases and embedding systems for retrieval-augmented generation (RAG)
Integrate agents with external APIs databases and enterprise systems
Establish MLOps practices for agent deployment monitoring and continuous improvement
Required Technical Skills
Core AI & ML:
Extensive experience with Google Vertex AI suite (Gemini Pro/Ultra PaLM 2 Codey Imagen)
Deep understanding of agentic AI patterns: ReAct Chain-of-Thought Tree of Thoughts and multi-agent workflows
Proficiency with LangChain LangGraph and agent orchestration frameworks
Experience with Model Context Protocol (MCP) for agent-to-agent communication
Knowledge of prompt engineering fine-tuning and model optimization techniques
Google Cloud Platform:
Vertex AI Workbench Pipelines and Model Registry
Cloud Functions Cloud Run and App Engine for serverless deployments
BigQuery for data processing and analytics
Cloud Storage Firestore and Cloud SQL for data management
Pub/Sub for event-driven architectures
Cloud Logging Monitoring and Error Reporting
Programming & Development:
Advanced Python programming (5 years)
Experience with FastAPI Flask or Django for API development
Containerization with Docker and Kubernetes (GKE)
Infrastructure as Code (Terraform Cloud Deployment Manager)
Version control with Git and CI/CD pipelines (Cloud Build GitHub Actions)
Data & Vector Systems:
Vector databases (Vertex AI Matching Engine Pinecone Weaviate or Chroma)
Embedding models and similarity search optimization
Knowledge graph construction and reasoning
Structured and unstructured data processing
Preferred Qualifications
Experience with additional agent frameworks (AutoGen CrewAI Semantic Kernel)
Knowledge of graph databases (Neo4j Amazon Neptune)
Familiarity with other cloud platforms (AWS Bedrock Azure OpenAI)
Understanding of function calling tool use and external API integration
Experience with streaming and real-time AI applications
Background in distributed systems and microservices architecture
Knowledge of AI safety alignment and responsible AI practices
Experience Requirements
10 years in software engineering with 3 years focused on AI/ML systems
2 years hands-on experience with production LLM applications
Demonstrated experience building and deploying agentic AI systems
Track record of architecting scalable cloud-native applications
Experience leading technical teams and mentoring junior developers
Education
Bachelors or Masters degree in Computer Science AI/ML or related technical field Preferred
Relevant certifications (Google Cloud Professional ML Engineer AI/ML specializations) preferred
Design and implement agentic AI architectures using Google Vertex AI models (Gemini PaLM Codey)
Develop and deploy AI agents using LangChain and Model Context Protocol (MCP) architectures
Build scalable production-ready AI systems leveraging GCP services including Vertex AI Pipelines Matching Engine and AI Platform
Implement multi-agent systems with complex reasoning planning and tool-use capabilities
Design and optimize vector databases and embedding systems for retrieval-augmented generation (RAG)
Integrate agents with external APIs databases and enterprise systems
Establish MLOps practices for agent deployment monitoring and continuous improvement
Required Technical Skills
Core AI & ML:
Extensive experience with Google Vertex AI suite (Gemini Pro/Ultra PaLM 2 Codey Imagen)
Deep understanding of agentic AI patterns: ReAct Chain-of-Thought Tree of Thoughts and multi-agent workflows
Proficiency with LangChain LangGraph and agent orchestration frameworks
Experience with Model Context Protocol (MCP) for agent-to-agent communication
Knowledge of prompt engineering fine-tuning and model optimization techniques
Google Cloud Platform:
Vertex AI Workbench Pipelines and Model Registry
Cloud Functions Cloud Run and App Engine for serverless deployments
BigQuery for data processing and analytics
Cloud Storage Firestore and Cloud SQL for data management
Pub/Sub for event-driven architectures
Cloud Logging Monitoring and Error Reporting
Programming & Development:
Advanced Python programming (5 years)
Experience with FastAPI Flask or Django for API development
Containerization with Docker and Kubernetes (GKE)
Infrastructure as Code (Terraform Cloud Deployment Manager)
Version control with Git and CI/CD pipelines (Cloud Build GitHub Actions)
Data & Vector Systems:
Vector databases (Vertex AI Matching Engine Pinecone Weaviate or Chroma)
Embedding models and similarity search optimization
Knowledge graph construction and reasoning
Structured and unstructured data processing
Preferred Qualifications
Experience with additional agent frameworks (AutoGen CrewAI Semantic Kernel)
Knowledge of graph databases (Neo4j Amazon Neptune)
Familiarity with other cloud platforms (AWS Bedrock Azure OpenAI)
Understanding of function calling tool use and external API integration
Experience with streaming and real-time AI applications
Background in distributed systems and microservices architecture
Knowledge of AI safety alignment and responsible AI practices
Experience Requirements
10 years in software engineering with 3 years focused on AI/ML systems
2 years hands-on experience with production LLM applications
Demonstrated experience building and deploying agentic AI systems
Track record of architecting scalable cloud-native applications
Experience leading technical teams and mentoring junior developers
Education
Bachelors or Masters degree in Computer Science AI/ML or related technical field Preferred
Relevant certifications (Google Cloud Professional ML Engineer AI/ML specializations) preferred
#48321
Employment Type
Full Time
Key Skills
Report This Job
Disclaimer: Drjobpro.com is only a platform that connects job seekers and employers. Applicants are advised to conduct their own independent research into the credentials of the prospective employer.We always make certain that our clients do not endorse any request for money payments, thus we advise against sharing any personal or bank-related information with any third party. If you suspect fraud or malpractice, please contact us via contact us page.
