Frontend Architect

Big Wombat LLC; New York (NY); Hybrid; USD 215,000 - 325,000; Full time

Job summary

Yaklabs is crafting a desktop AI app that turns knowledge workers into power users. The role focuses on building the frontend architecture and a generative UI engine that adapts to agent output and plugin panels.

You will own performance, data flow, and the runtime UI concepts that let the product evolve with new surfaces and workflows.

Qualifications

• Deep frontend fundamentals demonstrated by rendering models and debug tooling.
• Appreciation for performance and real-world profiling.
• Ability to design abstractions that outlast changing components.
• Experience with desktop-style UX, not just browser-based interfaces.
• Strong ownership and proactive problem solving.

Responsibilities

• Build the frontend architecture from scratch, defining components and data flow.
• Create a generative UI engine with dynamic surfaces and layouts.
• Implement chat-like experiences with streaming and tool calls.
• Ensure snappy performance on modest hardware and profile improvements.
• Develop frontend integration layers like OAuth and connection status.
• Define evolving abstractions to support future product changes.

Skills

Frontend fundamentals

Performance optimization

Abstractions

Desktop app experience

Ownership mindset

Job description

The job

You build the systems behind the UI: architecture, data flow, and the generative UI engine that makes Bonsai feel alive. The interface isn’t static: it adapts, extends, and rebuilds itself based on what agents are doing and what the person needs. That engine is yours to build.

Problems you’ll work on

These are examples, not lanes. You will move between them, while taking real ownership of the ones that match your interests.

• Software people can make their own: Most tools ask people to adapt to whatever interface the vendor ships. How do we let someone shape the software they use every day around their own work, without asking them to become a frontend engineer or fork the product?

• An interface as an extensible runtime: Users, agents, and plugins need to add new surfaces, interactions, and workflows inside Bonsai. What primitives and APIs let them build freely while keeping the result coherent, accessible, safe, and native to the product?

• Performance without closing the system: A customizable desktop app can run for days while plugins, panes, sessions, and live data accumulate. How do we keep it fast and robust on ordinary hardware without limiting what people can build?

What you’ll do

• Build the frontend architecture from scratch: component structure, state management, data flow across process boundaries.

• Build the generative UI engine: surfaces that render dynamically from agent output, plugin-defined panels, and user-customizable layouts. The UI is a runtime, not a set of hardcoded screens.

• Implement the chat experience: streaming, tool calls, multi-turn conversations, real-time feedback.

• Own performance on low-spec hardware. The product has to be snappy on an 8 GB corporate laptop. Measure, profile, and fix continuously.

• Build the integration layer on the frontend: OAuth flows, credential management, connection status, one-click setup experiences.

• Build the abstractions that let the product evolve. Today’s architecture has to support tomorrow’s. You’ll set that discipline.

Who you are

• Deep frontend fundamentals. Not “I’ve used React”: you understand rendering models, know how to debug from a flame graph, and have opinions about state management earned the hard way.

• You care about performance as a craft. You’ve profiled and optimized real applications, not just added lazy loading.

• You think in abstractions. You build interfaces that can survive the thing behind them changing completely.

• Desktop app experience or a strong appetite for it. It’s a different world from the browser.

Bonus

• You’ve shipped desktop apps to corporate or enterprise environments.

• You’ve worked cross-platform, on macOS and Windows.

• You’ve shipped PRs to open-source agentic harness projects.

About Yaklabs

Yaklabs is building a desktop AI application that turns knowledge workers into AI power users, without docs, API keys, or knowing what to ask for. One surface for agentic AI work: proactive, personalized, progressively powerful. The gap between AI power users and everyone else isn’t talent, it’s setup. We close it.

The team: Alex Goddijn spent four years at Palantir, then founded an agent harness company that was acquired by Poolside AI. Seb Goddijn led internal AI at Ramp. We’re building Bonsai so that kind of leverage isn’t limited to companies with their own internal AI team.

We have funding. Product and design work in person in New York City, and some engineering roles are remote. Small team, high intensity, no passengers.

Who we look for

• Technical builders with a domain edge. Everyone here is technically minded and can build and ship. You bring a distinctive strength in a domain: design, systems, product, infrastructure, or another area, and use it to take a problem from first principles to working software.

• First principles thinking. We’re building in a category that’s being defined in real time. Best practices don’t exist yet. You reason from the problem, not from what everyone else is doing.

• High agency and ownership. You don’t wait to be told what to do. You see what needs to happen, you go make it happen, and you own the outcome. At a team this size, there’s nobody to delegate to.

• Deep curiosity about AI tooling. Not just using ChatGPT or Copilot: you’re experimenting, writing your own tools, trying new agent frameworks the week they drop, forming opinions about what works and what doesn’t. The people building this product should be the most demanding users of the category. If you’ve shipped PRs to open-source agentic harness projects, tell us.

• You build compounding leverage. In the era of building with agents, one person doesn’t just ship one person’s work, they build the systems that build the product. Every person is amplified, and with that amplification comes the responsibility to build things that compound: skills, automations, agent workflows that make the next thing faster. This is a new way of working, and you’re excited to develop the skillset it demands.

The deal

• Early team. $215k to $325k base salary for US-based hires, plus meaningful equity.

• In person in New York City for product and design roles. Some engineering roles are remote, and each posting lists its location.

• You’ll shape the product, the culture, and the company. This is a founding-team role.

YakLabs is an equal opportunity employer. We consider every application without regard to race, color, religion, sex, gender identity, sexual orientation, national origin, age, disability, veteran status, or any other protected characteristic. If you need an accommodation at any point in the process, email [e-mail] and we will work it out with you. A person, not a machine, reads every application.