As a Google AI Solution Architect you will make an impact as the primary point of contact for all Google AI domain-related queries and issues. You will be a valued member of the team and work collaboratively with management, team members and client.
You will be responsible for designing, building, and deploying scalable, robust, multi-agent systems using Google’s Agent Development Kit (ADK), the Agent-to-Agent (A2A) protocol, and related tooling. You will partner with engineering teams, product stakeholders, and domain experts to translate business/functional requirements into agentic architectures that maximize modularity, reliability, and performance. You drive best practices for agent orchestration, inter-agent communication, state management, tool integrations, and cloud deployment (especially on Google Cloud / Vertex AI).
Your role is at the intersection of architecture, AI/ML, dev tools, and systems engineering. You must have deep familiarity with generative AI, agent frameworks, microservices, and distributed systems, as well as strong design ability to foresee complexity and orchestrate collaboration across agents.
We believe hybrid/remote work is the way forward as we strive to provide flexibility wherever possible. Based on this role’s business requirements, this is a hybrid position requiring 3-4 days a week in the client or Cognizant office. Regardless of your working arrangement, we are here to support a healthy work-life balance though our various wellbeing programs.
The working arrangements for this role are accurate as of the date of posting. This may change based on the project you’re engaged in, as well as business and client requirements. Rest assured; we will always be clear about role expectations.
Location: Remote
Role & Responsibilities:
Lead the architectural design of multi-agent AI systems using Google ADK, A2A, and related protocols (such as MCP)
Define agent roles, capabilities, workflows (sequential, parallel, loop), orchestration patterns, and error handling
Define inter-agent communication protocols, schema, and contract (e.g. JSON RPC, agent cards, task message formats)
Integrate agents with external tools, APIs, data sources (via MCP or other tool interfaces)
Define state, memory, session, and artifact management strategies
Define fallback, guardrails, validation, and feedback loops within agent systems
Lead prototyping, evaluation, and proof-of-concept builds for new agentic features
Provide guidelines for performance, scalability, observability, and latency in distributed agent systems
Define deployment, autoscaling, and management strategies (e.g. using Vertex AI Agent Engine, Cloud Run, etc.)
Work closely with data science / LLM teams to select, tune, and integrate models (e.g. Gemini, model variants)
Create reference architecture, reusable agent templates, blueprints, and best practices
Provide technical leadership and code reviews for agent / orchestration teams
Stay up-to-date with advances in multi-agent systems, protocol standards (A2A, MCP, etc.), and generative AI
Support troubleshooting, runtime monitoring, fault recovery, and agent debugging strategies
Required Skills:
5+ years in software architecture, distributed systems, or AI/ML engineering
Prior experience building complex systems involving microservices, orchestration, state management, event-driven design
Experience with agent frameworks or multi-agent / autonomous systems is a strong plus
Familiarity with Google Cloud, serverless compute (Cloud Run, GKE, etc.), and scaling distributed applications
Technical Skills
Proficiency in Python (or other languages used for agent frameworks)
Deep understanding of generative AI, LLMs, prompt engineering, chain-of-thought / planning techniques
Understanding of interservice communication (RPC, message queues, pub/sub, JSON protocols)
Strong design skills for modularization, interfaces, layering, versioning, and backward compatibility
Understanding of reliability, observability, monitoring, latency tradeoffs
Experience with API design, schema definition, JSON-based protocols
Familiarity with version control, CI/CD, containerization (Docker), cloud deployments
Soft / Leadership Skills
Ability to engage cross-functional teams (product, engineering, ML, operations)
Excellent communication, documentation, and architectural articulation skills
Ability to mentor, define standards, enforce consistency
Strategic thinking around roadmap, extensibility, and scaling
Nice-to-Have
Experience with Google’s ADK and A2A or similar agent toolkits
Experience with Model Context Protocol (MCP) or agent tool integrations
Experience with Vertex AI, or deploying agent systems on Google Cloud
Published contributions in agent / multi-agent AI, protocol design, or open source
Familiarity with security, governance, and policy considerations for autonomous agents
Applications will be accepted until 11/12/2025.
The annual salary for this position is between $100,890 – $162,000 depending on experience and other qualifications of the successful candidate.
This position is also eligible for Cognizant’s discretionary annual incentive program, based on performance and subject to the terms of Cognizant’s applicable plans.
Benefits : Cognizant offers the following benefits for this position, subject to applicable eligibility requirements:
· Medical/Dental/Vision/Life Insurance
· Paid holidays plus Paid Time Off
· 401(k) plan and contributions
· Long-term/Short-term Disability
· Paid Parental Leave
· Employee Stock Purchase Plan
Disclaimer: The salary, other compensation, and benefits information is accurate as of the date of this posting. Cognizant reserves the right to modify this information at any time, subject to applicable law.