Gemini AI Architect

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.

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 ():
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.

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  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.

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, Lang Graph, Mastra, Claude Agent SDK), observability and evals tooling (e.g., Agent Observability, Langfuse, Lang Smith, 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…