Senior Technical Specialist

• *Job Summary**
• --------------

Design, develop, and deploy production\-grade Multi\-Agent Systems (MAS) and agentic workflows using Gemini Enterprise

• Identify need for Pro Code Vs No Code design based on customer’s problem statement and data sources
• Design Deploy and custom agents using the Agent Development Kit (ADK), and Agent Platform AI Reasoning Engine and integrate with Gemini Enterprise
• Build native integrations across the Google Workspace Ecosystem (Docs, Drive, Gmail, Calendar, Meet) and NotebookLM for grounded enterprise research, document automation, and conversational discovery.
• Architect scalable short\-term session storage, conversation state persistence, and long\-term memory architectures across multi\-agent interactions.
• Implement end\-to\-end authentication and authorization perimeters for agents, Google Cloud services, and 3rd\-party SaaS integrations (e.g., Microsoft Entra ID / M365, Salesforce, Atlassian) using IAM, OAuth 2\.0, OIDC, and service identities.
• Enforce fine\-grained Access Control Lists (ACLs), user/group permission inheritance, and data governance policies to ensure agents strictly adhere to enterprise access boundaries.
• Utilize developer tooling including Agent CLI and Antigravity for local rapid prototyping, testing, emulation, distributed tracing, and root cause analysis (RCA).
• Architect Human\-in\-the\-Loop (HITL) workflows, ensuring seamless Interrupt and Resume patterns between autonomous agents and human experts for critical decision points.
• Build and maintain automated CI/CD pipelines (e.g., Cloud Build, GitHub Actions, GitLab CI) to manage versioned agent deployments, automated testing, and continuous regression evaluations.
• Implement advanced reasoning patterns such as Chain\-of\-Thought (CoT), ReAct, Plan\-and\-Solve, and Self\-Reflection to enhance agent reliability.
• Establish quantitative evaluation frameworks to measure agent trajectories, tool invocation precision/recall, and reasoning faithfulness.
• Collaborate directly with client engineering and architecture teams to deploy, validate, and operationalize enterprise agentic AI solutions in client environments.

• *Key Responsibilities**
• -----------------------

Design, develop, and deploy production\-grade Multi\-Agent Systems (MAS) and agentic workflows using Gemini Enterprise

• Identify need for Pro Code Vs No Code design based on customer’s problem statement and data sources
• Design Deploy and custom agents using the Agent Development Kit (ADK), and Agent Platform AI Reasoning Engine and integrate with Gemini Enterprise
• Build native integrations across the Google Workspace Ecosystem (Docs, Drive, Gmail, Calendar, Meet) and NotebookLM for grounded enterprise research, document automation, and conversational discovery.
• Architect scalable short\-term session storage, conversation state persistence, and long\-term memory architectures across multi\-agent interactions.
• Implement end\-to\-end authentication and authorization perimeters for agents, Google Cloud services, and 3rd\-party SaaS integrations (e.g., Microsoft Entra ID / M365, Salesforce, Atlassian) using IAM, OAuth 2\.0, OIDC, and service identities.
• Enforce fine\-grained Access Control Lists (ACLs), user/group permission inheritance, and data governance policies to ensure agents strictly adhere to enterprise access boundaries.
• Utilize developer tooling including Agent CLI and Antigravity for local rapid prototyping, testing, emulation, distributed tracing, and root cause analysis (RCA).
• Architect Human\-in\-the\-Loop (HITL) workflows, ensuring seamless Interrupt and Resume patterns between autonomous agents and human experts for critical decision points.
• Build and maintain automated CI/CD pipelines (e.g., Cloud Build, GitHub Actions, GitLab CI) to manage versioned agent deployments, automated testing, and continuous regression evaluations.
• Implement advanced reasoning patterns such as Chain\-of\-Thought (CoT), ReAct, Plan\-and\-Solve, and Self\-Reflection to enhance agent reliability.
• Establish quantitative evaluation frameworks to measure agent trajectories, tool invocation precision/recall, and reasoning faithfulness.
• Collaborate directly with client engineering and architecture teams to deploy, validate, and operationalize enterprise agentic AI solutions in client environments.

• *Skill Requirements**
• ---------------------

Must\-Have Skills

• Core Engineering \& Frameworks: Strong proficiency in Python with production\-level software engineering practices, along with deep, hands\-on experience building multi\-agent systems using Google ADK (Agent Development Kit) or comparable agentic frameworks.
• Gemini \& Workspace Ecosystem: Solid hands\-on experience deploying and customizing Gemini Enterprise, NotebookLM, and integrating with the broader Google Workspace Ecosystem (APIs, Add\-ons, Drive/Docs connectors).
• Memory \& State Architecture: Demonstrated expertise in managing agent session state, short\-term context caching, and durable long\-term memory backends (vector databases, relational/NoSQL session stores).
• Third Party Tools: Experience with MCP Connectors to securely integrate core third\-party platforms (e.g., iManage, NetDocuments, Relativity, DocuSign, MS Office Suite, Sharepoint, JIRA) with Gemini Enterprise.
• Auth \& Security: Strong understanding of authentication and authorization protocols (IAM, OAuth 2\.0, OIDC, Service Accounts, Workload Identity Federation) across Google Cloud and 3rd\-party SaaS platforms (Microsoft Entra ID, Salesforce, Atlassian).
• ACLs \& Permissions: Deep working knowledge of enterprise Access Control Lists (ACLs), identity federation, permission trimming, and role\-based access control (RBAC) across heterogeneous data sources.
• Developer Tooling: Proficiency in developer tooling such as Agent CLI and Antigravity for local simulation, debugging, prompt engineering, and execution graph tracing.
• CI/CD \& DevOps: Proven track record of configuring and maintaining automated CI/CD pipelines (Cloud Build, GitHub Actions) for agent containerization, deployment, and test automation.
• Evaluation \& Debugging: Practical knowledge of AI evaluation methodologies, trajectory analysis, and performing root cause analysis (RCA) on agent execution failures, tool errors, and prompt regressions.
• Client Collaboration: Strong technical communication, consulting acumen, and client\-facing collaboration skills within an Agile environment.

Good\-to\-Have Skills

• Experience with inter\-agent communication protocols such as Model Context Protocol (MCP) and Agent\-to\-Agent (A2A) architectures.
• Experience integrating agents with Enterprise Knowledge Graphs, structured ontologies, and hybrid vector search systems.
• Experience with enterprise data security frameworks such as Sensitive Data Protection (SDP/DLP) and VPC Service Controls (VPC\-SC).

Qualifications and Prior Experience

• Experience in software development, cloud solution architecture, and AI engineering (preferably on Google Cloud Platform).
• Proven track record of designing, building, and deploying production AI agents or enterprise GenAI solutions using ADK, Vertex AI, or Gemini.
• Hands\-on experience in customer\-facing technical delivery, solutions engineering, or forward\-deployed engineering (FDE) roles.
• Familiarity with enterprise Agile development lifecycles, sprint delivery, and stakeholder management.

• *Must Have Skill**
• ------------------

Google Cloud Platform (GCP),Python,Google Gemini,Agentic AI,CI/CD

• *Good to Have Skill**
• ---------------------

Model Context Protocol (MCP)

• *Other Requirements**
• ---------------------

Certifications and Trainings

• Professional Machine Learning Engineer
• Google Skill Boost labs/course
• Introduction to Gemini Enterprise :

https://partner.skills.google/course\_templates/1401

* Gemini Enterprise and NotebookLM

https://partner.skills.google/paths/3667

* Getting started with ADK

https://www.skills.google/catalog\_lab/32017

* Deployment

https://www.skills.google/catalog\_lab/32530

* Build and deploy multi agent

https://www.skills.google/course\_templates/1445