Software Engineer II, Frontend Agentic AI
About The Position
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.
Requirements
- 3+ years of front-end engineering experience with deep expertise in React, TypeScript, and modern state management (hooks, context, state machines).
- Experience building chat, copilot, or other LLM-powered interfaces in production.
- Hands-on experience with real-time UIs: WebSockets, server-sent events, streaming rendering, and reconnection handling.
- Strong product sense and the ability to design interaction patterns where no standard exists yet.
- Experience integrating front ends with LLM APIs and handling streamed, partial, and structured model outputs.
- Experience translating designs into fast, polished, responsive production code.
- Strong communication skills and comfort working directly with users to refine the experience.
Nice To Haves
- Shipped a chat or agent product used by thousands of users.
- Familiarity with agent frameworks (LangChain, LangGraph, or equivalent) and AI front-end SDKs such as the Vercel AI SDK.
- Experience with design systems, accessibility standards, and component library ownership.
- Experience visualizing complex processes: timelines, graphs, or workflow builders.
- Prior experience at a high-growth venture-backed AI or SaaS startup.
Responsibilities
- 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 interface where users design and configure their own digital workers in natural language.
- Manage complex client state for long-running agent sessions: reconnection, optimistic updates, partial results, and failure recovery.
- Create a reusable component library for agentic patterns so every new worker ships with a consistent, polished interface.
- Handle model output honestly in the UI: citations, uncertainty, errors, and empty states that tell the user the truth.
- Work daily with backend and agent engineers to shape the APIs and event streams the interfaces consume.
- Optimize for performance across devices and keep the experience fast while an agent streams thousands of events.
Benefits
- equity (where applicable)
- bonus
- health, dental and vision insurance
- 401(k)
- flexible spending account
- paid leave (including PTO and parental leave)
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
