Software Engineer II, Frontend Agentic AI

Secure Every Identity, from AI to Human

Identity is the key to unlocking the potential of AI. Okta secures AI by building the trusted, neutral infrastructure that enables organizations to safely embrace this new era. This work requires a relentless drive to solve complex challenges with real-world stakes. We are looking for builders and owners who operate with speed and urgency and execute with excellence.

This is an opportunity to do career-defining work. We're all in on this mission. If you are too, let's talk.

The Software Engineer II Opportunity

We are looking for a software engineer to build the interfaces people use to work with autonomous AI workers. This is not a dashboard job. Our users chat with agents that run for hours, steer them mid-task, inspect what an agent remembers, approve or reject its actions, and watch it work in real time.

You will own those surfaces: the chat experience, the memory and context views, the live run timeline, and the approval flows that keep a human in charge. You will define what agentic interfaces look like—because most of the patterns you will ship do not exist yet. This is a senior individual contributor role requiring a minimum of 5 years of relevant experience.

About You

• Proven Product Builder: You have built and shipped products that users love and have seen the direct impact of your work at scale.
• End-to-End Ownership: You take pride in owning projects from initial concept to launch and are comfortable wearing multiple hats to get the job done.
• AI & Tech Innovator: You stay ahead of the curve, eager to explore and implement the latest technologies, particularly in AI and LLM front-end paradigms.
• Collaborative Partner: You thrive in a high-bandwidth team environment and work effortlessly with both technical and non-technical partners.
• Driven & Ambitious: You have a hunger for success and want to build at a fast-growing company with big goals.

What you’ll be doing

• Build the conversational interface for long-horizon agents: streaming responses, tool calls shown as they happen, pause and interrupt controls, and mid-task steering.
• Design and ship memory management interfaces that let users see what an agent knows, edit or delete memories, and understand what context the agent is using and why.
• Build live agent run views: plans, steps, artifacts, retries, and results, rendered in real time over WebSockets or server-sent events.
• Build human-in-the-loop approval surfaces for agent actions that write to external systems, with clear diffs of what the agent is about to do.
• Build the Worker Builder interfa