Gemini AI Architect

VLink Inc; San Ramon (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

VLink Inc. is seeking an AI Architect to join the Enterprise AI team, evaluating AI fit, building tools and platforms, and enabling teams to adopt modern AI development patterns across the organization.

You will design and ship Custom Agents using the ADK, orchestrate multi-model deployments, implement AI governance, and drive scalable, production-grade solutions across Google and Microsoft ecosystems.

Qualifications

• 7+ years of professional software engineering with at least 2 years focused on applied AI in production.
• Proficient in Python and/or Go, with ability to read and write the other.
• Proven experience building and scaling multi-agent or agent-driven systems in production.
• Hands-on experience with Google Gemini Enterprise and the ADK, or comparable enterprise agent platforms.

Responsibilities

• Think AI-first—assess where agentic approaches outperform conventional solutions and define the success metrics.
• Design agentic systems using the ADK, tool orchestration, agent reasoning, memory, and MCP integrations.
• Define and implement AI governance patterns: identity, security, data lineage, and observability.
• Enable multi-model routing and BYOLLM across Gemini, Claude, LLAMA, and OpenAI, balancing capability and cost.

Skills

Python

Go

Agent-based systems

Tools

Google Gemini Enterprise

ADK

LangSmith

Langfuse

Kubernetes

Job description

VLink, founded in 2006, is a leading global provider of software engineering services with next-gen technologies and best-in-class talent. Our Headquarters are in the U.S, and we have offices in 7+ countries from North America-Europe to APAC, with expansion plans in the Middle East.

About the role:

As an AI Architect on the Enterprise AI team, you'll evaluate where AI fits, build the tools and platforms that make it practical, and enable teams across the company to adopt modern AI development patterns - including LLM orchestration, agentic workflows, and model governance - on Google Gemini Enterprise. You'll design and ship Custom Agents using the Agent Development Kit (ADK), register them in the Agent & Tool Registry, wire them to enterprise systems via BYO and vendor-managed MCP servers, and enforce Agent Identity, Security, and Observability end to end. You stay hands-on and outcomes-oriented: prototyping, evaluating emerging AI technologies, and shipping solutions that make the organization measurably more efficient.

You'll be building on our Google Gemini Enterprise stack:

Platform surface (gemini.google.com): Google Enterprise business apps, Custom Agents, and enterprise Search UX as the primary experiences delivered to internal users.

Agentic Studio Platform: ADK & runtime & model training, Agent & Tool Registry, Agent Identity, Agent Security, and Agent Observability — the build, govern, and operate layer for all agents.

Multi-model / Bring Your Own LLM (BYOLLM): flexible model routing across Gemini, Claude, LLAMA, and OpenAI, selecting the right model per use case, cost, and quality target.

Integration & data layer: enterprise data sources (Google Workspace, Microsoft 365, and others), BYO MCP servers (application/tool-centric), and vendor-managed MCP servers & agents.

What You'll Do

Think AI-first - assess where agentic approaches genuinely outperform conventional solutions, then own the quality bar: build automated evals, simulation tests, and regression frameworks that keep our Gemini Enterprise agents reliable and improving as they scale, integrated with Agent Observability.

Design agentic systems on the Agentic Studio Platform - Custom Agent development with ADK, tool orchestration, agent reasoning, memory, MCP integrations (both BYO and vendor-managed servers), and human-in-the-loop workflows.

Define and implement AI governance patterns - guardrails, data lineage, auditability, and responsible AI practices using Agent Identity, Agent Security, and the Agent & Tool Registry to ensure our agentic systems are safe, compliant, and trustworthy.

Enable multi-model flexibility (BYOLLM) - implement model routing and fallback across Gemini, Claude, LLAMA, and OpenAI, balancing capability, latency, and inference cost.

Drive adoption through pilots, proofs-of-concept, and scalable implementations across engineering teams, delivered through gemini.google.com surfaces (business apps, Custom Agents, and Search UX).

Collaborate with various business functions, product, security, and platform teams to translate AI use cases into production-grade, end-to-end solutions connected to enterprise data sources across Google and Microsoft ecosystems.

What We’re Looking For

7+ years of professional software engineering, with at least 2 years focused on applied AI in production systems.

Proficient in Python and/or Go; comfortable reading and writing in the other.

Proven experience building and scaling multi-agent or agent-driven systems in production - real-world operational ownership, not just simple LLM workflows.

Hands-on experience with Google Gemini Enterprise and the Agent Development Kit (ADK), or comparable enterprise agent platforms, including agent runtime, agent/tool registration, identity, and observability.

Hands-on experience with modern agent ecosystems, including frameworks (e.g., Google ADK, LangGraph, Mastra, Claude Agent SDK), observability and evals tooling (e.g., Agent Observability, Langfuse, LangSmith, Braintrust), MCP implementations, and leading AI SDKs across a multi-model / BYOLLM environment (e.g., Gemini/Vertex AI, Anthropic (Claude), OpenAI, LLAMA).

Strong systems and backend architecture fundamentals - designing scalable, reliable systems and handling infrastructure, performance, failure modes, cost, and deployment concerns.

Good understanding of cloud-native environments, with Google Cloud (GCP) and Vertex AI strongly preferred (and/or AWS) - compute, storage, networking, and managed AI services.

Experience designing and integrating with enterprise APIs (REST, GraphQL) including authentication and authorization patterns (OAuth2, SAML, API keys, RBAC), and connecting agents to enterprise data sources across Google Workspace and Microsoft 365. Comfortable working with backend databases (SQL and NoSQL) — writing queries, understanding data models, and building data access layers that enforce role-based access control aligned with Agent Identity and Agent Security.

Strong cross-functional collaborator and communicator, able to partner with Product, Operations, and domain experts to deliver end-to-end systems with measurable real-world impact.

A force-multiplier on the team — you raise the bar for clarity of thinking, system design standards, and team execution.

Nice to Have

Direct experience deploying agents on Google Gemini Enterprise / Agentic Studio Platform (Custom Agents, Search UX, business apps) in production.

Experience with AI evaluation tooling (Agent Observability, Langfuse, LangSmith, Braintrust, or custom eval frameworks).

Experience building custom MCP servers (both application/tool-centric BYO servers and vendor-managed servers & agents), not just consuming them.

Familiarity with containerization and orchestration (Docker, Kubernetes) and GCP-native deployment (Cloud Run, GKE).

AI-native builder with high velocity and ownership - intellectual curiosity, rapid adoption of new tools, bias to action, and the ability to drive ambiguous problems from concept to production.

Hands-on experience with inference cost optimization across a multi-model/BYOLLM setup -managing spend as agent deployments scale.

Experience using AI-powered coding agents (e.g., Claude Code, GitHub Copilot, Cursor, Windsurf) to accelerate development workflows - rapid prototyping, code generation, debugging, and test writing.

Experience with RAG (Retrieval-Augmented Generation) architectures and document retrieval pipelines - vector databases, embedding models, chunking strategies, and hybrid search - for building agents that answer questions grounded in enterprise documentation and data sources.

EEO Statement

VLink is an Equal Opportunity Employer committed to fostering an inclusive environment where diversity is celebrated. All qualified applicants will be considered for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or veteran status. Employment is contingent upon successful completion of a background check. Applicant information will be handled in accordance with VLink's privacy policy.