Coursera and Udemy are now one company, bringing together two mission-driven brands to create the world’s most powerful platform for turning learning into progress.
Together, we help more than 300 million learners and 12,000+ enterprise customers build the skills they need for a world being reshaped by AI.
Responsibilities
Design how AI agents access and understand Coursera’s internal data and knowledge, so agents retrieve the right information rather than guessing or over-fetching.
Establish reusable patterns for RAG, semantic search, structured data access, and enterprise context, partnering with the Data team on existing data models and pipelines.
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, so agentic solutions are reliable and production-ready.
Build technical guardrails that enforce—not just document—who can build what, what data and systems an agent can access, and what gets logged for audit and review.
Design defenses specific to agentic AI, including agent identity and access control, least-privilege permissions, prompt injection, data leakage, secure credentials, and safe tool execution.
Extend and mature Coursera’s self-serve deployment path so AI-assisted, conversational development ships through automated testing, security checks, and evaluation gates.
Design caching, model routing, token and context optimization, and usage monitoring so AI adoption can scale without costs growing linearly.
Define agent ownership, lifecycle management, production-readiness standards, 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, integrations, and downstream impacts.
Establish standards for reliability, observability, incident response, security, operational ownership, and continuous improvement across AI platforms and solutions.
Requirements
Hands-on architecture experience.
Experience with RAG, semantic search, structured data access, and enterprise context.
Experience with agent orchestration, tool use, multi-step workflows, state management, and human-in-the-loop decisions.
Experience with testing, evaluation, guardrails, retries, observability, and failure recovery for agents.
Experience with agent identity and access control, least-privilege permissions, prompt injection, data leakage, secure credentials, and safe tool execution.
Experience with CI/CD automation, automated testing, security checks, and evaluation gates.
Experience with LLM cost and performance optimization, caching, model routing, token and context optimization, and usage monitoring.
Experience with enterprise systems and integration architecture, APIs, enterprise tools, and Model Context Protocol (MCP) or comparable integration standards.
Experience with production readiness and operational excellence, reliability, observability, incident response, security, operational ownership, and continuous improvement.