This is a remote position.
Role : Senior Engineer – Google Agentic AI (ADK, Agent Development & Deployment
Work Location: Remote
No. of Internal interview:1
Client interview required:1
Job Description:
Position Overview
We are seeking a highly skilled Google Agentic AI Engineer to design, develop, deploy, and operate enterprise-grade AI agents using Google Agent Development Kit (ADK), Vertex AI Agent Builder, Gemini Models, and Google Cloud Platform (GCP). The candidate will be responsible for building intelligent, scalable, secure, and production-ready multi-agent systems that integrate with enterprise applications, APIs, and knowledge repositories.
Key Responsibilities
Agent Development
- Design and develop AI agents using Google ADK.
- Build autonomous and multi-agent workflows leveraging Gemini models.
- Implement agent orchestration, memory management, session handling, and tool integrations.
- Develop custom tools, function calling mechanisms, and API integrations for enterprise use cases.
- Design agent collaboration patterns using A2A and MCP standards.
- Build reusable agent templates and frameworks to accelerate solution delivery.
Agent Deployment & Operations
- Deploy agents using Vertex AI Agent Builder and Agent Engine.
- Build scalable production deployments on GCP services including Cloud Run, GKE, and Vertex AI.
- Implement agent observability, monitoring, tracing, logging, and performance optimization.
- Define SLIs, SLOs, and operational dashboards for AI workloads.
- Support production operations, incident management, and continuous improvement initiatives.
Enterprise AI Solutions
- Develop RAG solutions by leveraging Vertex AI Search, Vector Search, and enterprise knowledge sources.
- Integrate agents with enterprise systems such as Salesforce, ServiceNow, SharePoint, Jira, Confluence, and custom APIs.
- Implement context engineering, knowledge graph integration, and enterprise grounding techniques.
- Build workflow automation agents, diagnostic agents, customer support assistants, and operational bots.
Security, Governance & Compliance
- Design secure AI architectures following enterprise governance standards.
- Implement guardrails, content filtering, hallucination detection, DLP, access control, and identity management.
- Ensure compliance with enterprise security, privacy, and regulatory requirements.
- Drive AI governance, monitoring, risk management, and responsible AI practices.
Engineering Excellence
- Establish coding standards, evaluation frameworks, and testing strategies for AI agents.
- Mentor engineering teams on Agentic AI architecture and development best practices.
- Conduct architecture reviews and technical assessments.
- Stay current with advancements in Agentic AI, LLMs, ADK, MCP, A2A, LangGraph, CrewAI, and related ecosystems.
Mandatory Skills
Google Agentic AI
AI/LLM Engineering
- Prompt Engineering
- RAG Architecture
- Vector Databases
- Knowledge Graphs
- Agent Evaluation Frameworks
- LLM Fine-Tuning and Optimization
- AI Observability and Monitoring
Cloud & Development
- Google Cloud Platform (GCP)
- Python
- REST APIs
- Kubernetes (GKE)
- Cloud Run
- Docker
- GitHub Actions / CI-CD
- Infrastructure as Code (Terraform preferred)
Data & Integration
- BigQuery
- Vertex AI Search
- Vector Search
- Enterprise API Integration
- MCP and A2A Protocols
Preferred Skills
- LangGraph
- LangChain
- CrewAI
- LlamaIndex
- OpenAI / Anthropic / Gemini ecosystems
- AI Security & Governance
- MLOps / LLMOps
- Event-driven architecture
- Real-time AI applications
- Enterprise SaaS integrations
- AI Cost Optimization
Qualifications