Enterprise Agentic AI Architect

Overview

Design and build the core agentic AI architecture that Coursera's AI Builders and business pods will run on, as a hands-on architecture leader who also builds people capability.

What you'll do

• Design how AI agents access and understand Coursera's internal data and knowledge, and establish reusable patterns for RAG, semantic search, structured data access, and enterprise context, partnering with the Data team.
• Design reusable patterns for agent orchestration, tool use, multi-step workflows, state management, and human-in-the-loop decisions.
• Build the engineering harness around agents, including testing, evaluation, guardrails, retries, observability, and failure recovery.
• Build technical guardrails that enforce who can build what, what data and systems an agent can access, and what gets logged for audit and review.
• Establish standards for agent ownership, lifecycle management, and production readiness.
• Design security architecture specific to agentic AI, including agent identity and access control, least-privilege permissions, prompt injection, data leakage, secure credentials, and safe tool execution, in coordination with Security.
• Extend and mature the self-serve deployment path so AI-assisted development ships through automated testing, security checks, and evaluation gates.
• Design caching, model routing, token and context optimization, and usage monitoring so AI adoption scales without costs growing linearly, and establish cost, latency, quality, and usage metrics.
• Define the agent operating model, adoption metrics, and reusable patterns so business teams can scale AI capabilities consistently across functions.
• Turn ambiguous business problems into scalable technical direction, practical roadmaps, architecture decisions, and production delivery.
• Design AI solutions that understand dependencies across enterprise systems, business processes, and integrations, and establish reusable patterns for APIs, enterprise tools, and Model Context Protocol (MCP) or comparable standards where appropriate.
• Establish standards for reliability, observability, incident response, security, operational ownership, and continuous improvement across AI platforms and solutions.
• Partner with Engineering leadership, IT, the Data team, the Security team, and business pods, and support change management and enablement.
• Build, coach, and develop the architecture and engineering capability required to scale the platform, including hiring, delegation, performance management, and clear ownership across teams.
• Report directly to the VP, AI and Operations, with regular updates on architecture progress, risks, business impact, and resourcing needs.

What you'll need

• 12+ years of experience with clear progression from engineer to senior/staff engineer to architect leader, including ownership of platforms or infrastructure used by multiple teams.
• Hands-on experience with agentic AI frameworks and orchestration (e.g., LangGraph or comparable).
• Familiarity with Model Context Protocol (MCP) or similar standards for connecting AI systems to enterprise data and tools.
• Experience designing agent harnesses, evaluation frameworks, guardrails, testing, observability, and failure recovery for production AI systems.
• Practical experience with enterprise context architecture, RAG, semantic search, or structured data access.
• Practical experience with LLM cost and performance engineering, including prompt caching, model routing, and token economics, with quantifiable results.
• AI security fundamentals, including access control, data isolation, prompt injection defense, and secure tool execution.
• CI/CD, cloud infrastructure, APIs, and production operations experience.
• Experience defining enterprise AI architecture, reusable platform patterns, operating models, or governance standards across multiple teams.
• Direct people-management experience, including hiring, coaching, delegation, performance development, and building technical leadership capacity.
• Experience measuring AI adoption, productivity, quality, reliability, cost, and business value.
• Hands-on experience taking architecture from design through implementation, deployment, observability, and production operations.
• Strong architecture decision-making and communication skills, with the ability to align technical and business stakeholders around trade-offs involving value, risk, cost, and execution.

Details

• Location: India.