AI Architect

Zensar Technologies•San Jose, CA

About The Position

Zensar Technologies is seeking a hands-on Lead AI Systems Architect to design, build, and scale its next-generation AI ecosystem. The role focuses on architecting and implementing agent-to-agent frameworks, Model Context Protocol (MCP) integrations, and an internal AI development platform. The architect is expected to write production-ready code and translate AI research into robust software, while serving as a bridge between engineering teams and stakeholders. The position will shape the architecture and technical roadmap for AI systems and platform capabilities, including multi-agent orchestration, secure connections between LLMs and enterprise resources, and workflows for training, testing, and deploying models. It also involves setting engineering standards, mentoring engineers, collaborating across product, data, and security teams, and communicating technical direction to both technical and non-technical audiences. Zensar describes its workplace as open and innovation-oriented, with offices designed to encourage creativity and communication. The company states that it provides a comprehensive benefits package to full-time employees. Applicants must be legally authorized to work with Zensar; visa sponsorship may be available for qualified applicants for certain positions.

Requirements

At least 10 years of software architecture experience, including at least 3 years building and deploying production-grade LLM applications and AI systems.
Deep expertise in multi-agent frameworks such as LangGraph, AutoGen, or CrewAI.
Hands-on experience with prompt engineering, Retrieval-Augmented Generation (RAG) pipelines, and vector databases.
Proven experience designing or implementing Model Context Protocol (MCP) or similar context-sharing and tool-calling protocols.
Strong programming skills in Python, TypeScript, or Go.
Extensive experience with cloud-native technologies, including AWS, GCP, or Azure, Kubernetes, and Docker.
Demonstrated ability to create high-throughput, low-latency AI platforms.
Excellent verbal and written communication skills, including the ability to author comprehensive architecture RFCs and lead technical discussions.
Leadership experience mentoring engineers and driving cross-functional technical alignment.
A bachelor's degree or higher in Computer Science, Engineering, or a related field.
Must be legally authorized to work with Zensar.

Responsibilities

Design and implement multi-agent orchestration frameworks, including autonomous negotiation, task delegation, state management, and secure inter-agent communication.
Architect, develop, and operate scalable MCP servers and clients that connect LLMs to data sources, tools, and enterprise environments.
Define the technical roadmap for the internal AI development platform, emphasizing throughput, latency, and seamless CI/CD pipelines.
Write production-grade code, create prototypes, and establish engineering best practices for AI application development.
Standardize architectural patterns, guidelines, and reusable components across the organization.
Mentor junior engineers and foster continuous learning in AI and agentic technologies.
Collaborate with product, data, and security teams to align AI solutions with business objectives and compliance requirements.
Lead technical discussions, produce detailed architecture RFCs, and communicate complex concepts to non-technical stakeholders.
Evaluate and integrate emerging AI SDKs, vector databases, and cloud-native services.
Monitor system performance, conduct root-cause analysis, and drive continuous improvement of AI services.