Architect

We’re a bunch of hardworking, fun-loving, people-oriented technology enthusiasts. We love what we do, and we’re passionate about helping our clients thrive in an increasingly complex digital world. Zensar is an organization focused on building relationships with our clients and with each other—and happiness is at the core of everything we do. In fact, we’re so into happiness that we’ve created a Global Happiness Council, and we send out a Happiness Survey to our employees each year. We’ve learned that employee happiness requires more than a competitive paycheck, and our employee value proposition—grow, own, achieve, learn (GOAL)—lays out the core opportunities we seek to foster for every employee. Teamwork and collaboration are critical to Zensar’s mission and success, and our teams work on a diverse and challenging mix of technologies across a broad industry spectrum. These industries include banking and financial services, high-tech and manufacturing, healthcare, insurance, retail, and consumer services. Our employees enjoy flexible work arrangements and a competitive benefits package, including medical, dental, vision, 401(k), among other benefits. If you are looking for a place to have an immediate impact, to grow and contribute, where we work hard, play hard, and support each other, consider joining team Zensar! Zensar is looking for a AI Architect in San Ramon, CA. This position is open for Full Time with excellent benefits and professional growth opportunities. About the Role You are the architect for the Governance Control Tower — the single person who owns its design end to end and who the platform leadership deals with directly. You will define the architecture standards and the checklist every agent must clear before it goes live, run the review board relationship, and lead a cross-functional delivery pod that implements and then operates the platform. You stay hands‑on. This role sets the standard and then proves it works — designing the reusable agent layer, resolving the identity and retrieval questions that determine whether the governance model is real or decorative, and carrying the technical credibility. You will lead the pod through two phases: build, standing the Control Tower up; then run, where a right‑sized support pod takes over day‑to‑day operation and you remain the architectural owner. The Platform Environment: Gemini Enterprise — the employee-facing surface: managed chat, enterprise search, agent gallery, and app‑scoped experiences serving all business functions. Agent Platform — the build, govern and operate layer: ADK and agent runtime, agent and tool registry, agent identity, agent security, agent observability. Custom front-end applications calling Gemini Enterprise via API, with end‑user identity propagation. Integration and data layer — enterprise connectors across Google Workspace and Microsoft 365, BYO and vendor‑managed MCP servers, and federated retrieval across function‑scoped data stores. What You’ll Own The Control Tower is delivered as five workstreams. You own the architecture across all five. Governance & Standards Registry & Gateway Operations Identity & Entitlement Enforcement Observability & Cost Control Across all of it, you will also: Design the reusable top‑level agent layer — orchestrator, context engineering, retrieval, synthesis and response — that acts as the common entry point for every application on the platform, so that query planning, grounding, re‑ranking and citation behave identically wherever a user enters. Lead the pod: set technical direction, review the work, and be accountable for what ships. Translate between the platform leadership and the delivery team, turning direction into architecture and architecture into a defensible plan. Hold the quality bar — evaluation datasets, threshold gates, regression testing — so the platform stays reliable as agent count scales. Experience: 10+ years in software engineering and architecture, with 3+ years designing and running applied AI systems in production. Proven experience as the architectural owner of an enterprise platform — you have set standards that other teams had to follow, and made them stick. Hands‑on with Google Gemini Enterprise and ADK, or a directly comparable enterprise agent platform, including agent runtime, registration, identity and observability. Deep experience with multi‑agent systems in production — orchestration, routing, tool use, memory, human‑in‑the‑loop — with real operational ownership rather than prototype work. Strong grounding in RAG and retrieval architecture: vector stores, embedding models, chunking strategy, hybrid search, and the difference between retrieval that works in a demo and retrieval that works across a messy enterprise estate. Identity and access depth. OAuth2, SAML, RBAC, token exchange, service‑account versus end‑user credential propagation, and document‑level ACL mapping from source systems into a retrieval layer. You understand why this determines whether governance is real. Proficient in Python; comfortable with Go or an equivalent second language. Experience with MCP — building servers, not only consuming them. Solid cloud‑native and systems fundamentals, with GCP strongly preferred (Cloud Run, GKE, Vertex AI, networking, IAM). Cost awareness at scale — token and inference spend management across a growing agent estate. Nice to Have: Production deployment of agents on Gemini Enterprise / Agent Platform, including custom agents and search experiences. Experience with AI evaluation tooling — agent observability platforms, Langfuse, LangSmith, Braintrust, or custom eval frameworks. Multi‑model routing and fallback across Gemini, Claude, OpenAI or Llama, balancing capability, latency and cost. Enterprise data connector work across Google Workspace and Microsoft 365, including entitlement‑aware indexing. Experience standing up an AI governance function — review boards, architecture checklists, audit evidence — inside a regulated or multi‑entity enterprise. Containerisation and orchestration (Docker, Kubernetes). Fluent use of AI‑assisted development tooling to move quickly. What Success Looks Like By month three: the architecture checklist and go‑live gate are agreed and in use, the registry and gateway are operating, and the first wave of agents has gone live through the governed path rather than around it. By month six: identity and entitlement enforcement is live end to end, retrieval is grounded across the priority data domains, and the leadership can see per‑agent cost and quality telemetry without asking anyone to compile it. Education: Bachelor’s Degree Zensar believes that diversity of backgrounds, thought, experience, and expertise fosters the robust exchange of ideas that enables the highest quality collaboration and work product. Zensar is an equal opportunity employer. All employment decisions shall be made without regard to age, race, creed, color, religion, sex, national origin, ancestry, disability status, veteran status, sexual orientation, gender identity or expression, genetic information, marital status, citizenship status or any other basis as protected by federal, state, or local law. Zensar is committed to providing veteran employment opportunities to our service men and women. Zensar is committed to providing equal employment opportunities for people with disabilities or religious observances, including reasonable accommodation when needed. Accommodation made to facilitate the recruiting process are not a guarantee of future or continued accommodation once hired. All applicants must be legally authorized to work with Zensar. Zensar values your privacy. We’ll use your data in accordance with our privacy statement located at: #J-18808-Ljbffr