Agentic AI Architect

Persistent Systems; Bengaluru; On-site; INR 2,800,000 - 5,200,000; Full time

Job summary

Persistent Systems in Bengaluru seeks a highly experienced Agentic AI Architect to lead design and implementation of AI-driven enterprise solutions, leveraging Vertex AI and modern cloud platforms.

You will shape AI strategy, architect scalable agents, and collaborate with business and technology stakeholders to translate goals into measurable outcomes, while defining governance, risk, and performance metrics.

Qualifications

• 10–15 years of industry experience in AI architecture.
• Proven ability to design scalable agentic AI solutions.
• Experience with AI governance, risk, and compliance considerations.

Responsibilities

• Study current business processes and map AI participation to workflows.
• Define AI-enabled boundaries, approvals, and escalation paths.
• Translate business goals into measurable AI outcomes.
• Design end-to-end architectures including models, RAG, and memory.
• Collaborate with stakeholders to articulate risks and success metrics.

Skills

Agentic AI

LLMs

Autonomous AI systems

Cloud-native architectures

Job description

We are seeking a highly experienced Agentic AI Architect with 10-15 years of industry experience to lead the design, architecture, and implementation of next-generation AI-driven solutions. The ideal candidate will possess deep expertise in Agentic AI frameworks, large language models (LLMs), autonomous AI systems, and cloud-native architectures. This role involves collaborating with business and technology stakeholders to define AI strategies, architect scalable intelligent agents, and deliver enterprise-grade AI solutions leveraging Vertex AI and modern cloud platforms.

• Role: Agentic AI Architect
• Experience: 10 to 15 Years
• Job Type: Full Time Employment

What You'll Do:

• Study the current business process, including users, decisions, handoffs, systems, information sources, exceptions, delays, controls and failure points.
• Separate problems that need AI reasoning from those better solved through process correction, rules, search, analytics, workflow automation or conventional software.
• Define the target process and show exactly where an AI assistant or agent participates, where deterministic controls apply and where a person must review or approve.
• Convert business goals into measurable outcomes such as reduced handling time, improved first-time accuracy, fewer manual handoffs, faster information retrieval, lower rework or better control compliance.
• Establish the current KPI baseline, target improvement, measurement method, data source, reporting frequency and business owner before claiming value.
• Explain expected capabilities, limitations, uncertainty, failure modes, dependencies and residual risks in language understood by business and technology stakeholders.
• Design end-to-end architectures covering models, RAG, knowledge sources, agent orchestration, tools, APIs, state, memory, user channels, identity, permissions and human escalation.
• Define clear boundaries for agent autonomy, including which actions are read-only, which require confirmation and which