Design Engineer - m/f/d

Über diese Stelle

WHERE EUROPE'S ENTERPRISES ADOPT AI

Langdock is the AI platform used by more than 10,000 companies to give employees secure access to the leading AI models, to build and share agents and to automate repetitive workflows. We have grown past $40M ARR while remaining a small team, and we care deeply about operating efficiently across the entire company.

For many enterprises, Langdock is becoming the place where most of the net-new work is produced. As people and agents create more documents, analyses, decisions, and automations inside AI interfaces, the context and data behind that work accumulate within Langdock. This gives us the opportunity to earn a larger role in their technology stack by building a platform they choose to rely on.

Our ambition is to build that platform for European enterprises while preserving their control over data, model providers, and deployment environments. We have made meaningful progress at the application layer, but much of the foundation beneath it still needs to be built.

You can watch the Meet the engineering team video to get a feeling for how we work.

THE ROLE

Design Engineers own the experience and visual language of Langdock, then turn that design into working software. You take an ambiguous product problem from the user's workflow through information architecture, interaction design, visual execution, and production code.

The source of truth is the product, not a handoff. Figma is useful for exploration, but the decisive design work happens in React, where real data, latency, permissions, edge cases, and responsive behavior are visible. You are responsible for whether the final interaction is clear, coherent, and technically sound.

This role spans individual product surfaces and the systems behind them. You will shape major workflows yourself, build the component library and design system that raise the quality of work across the company, and help other engineers make better interface decisions.

WHAT YOU MIGHT WORK ON

- Human-agent collaboration. Design how people give agents context, steer work in progress, approve actions, inspect tool calls, recover from failure, and review complex outputs. The challenge is to make powerful multi-step systems understandable without reducing the experience to another chat interface.

- Dense enterprise workflows. Make permissions, governance, configuration, evaluations, and workspace administration understandable to occasional users without slowing down experts. Find the hierarchy and interaction model that preserve necessary complexity without making the product feel heavy.

- Creating work with agents. Define the interfaces where people and agents produce and revise documents, analyses, spreadsheets, applications, and other structured work together. Show progress, changes, sources, and control clearly enough that users can understand and trust the result.

- The design system. Build and evolve reusable components, interaction patterns, typography, motion, and layout principles that keep a growing product coherent. Make the high-quality choice the fastest choice for engineers working across the product.

- Prototypes and production interfaces. Turn uncertain ideas into realistic software quickly enough to expose difficult interaction and technical questions before the team commits to an approach. Then implement responsive, accessible product surfaces in React and Tailwind CSS, going into the backend when a strong end-to-end result requires it.

- Product storytelling. Apply the same visual standard to launches, product pages, demos, and other materials that explain what Langdock does. Work in code where appropriate and make sure the way we present the product matches the quality of the product itself.

TECH STACK

- TypeScript, React, Next.js, and Tailwind CSS in one Bazel monorepo

- Node.js, PostgreSQL, and Prisma when work crosses into the backend

- Figma for exploration

- Linear for planning and GitHub for code review

You should be strong in the frontend stack and comfortable learning enough of the surrounding system to finish work end to end.

HOW WE WORK

- We operate with high trust and autonomy in squads of 3 to 4 engineers. A squad owns its roadmap, prioritization, technical decisions, and operation in production. Engineers are expected to find the context they need, ask for input when it improves the outcome, and move work forward without waiting for every next step to be assigned.

- We align asynchronously before scheduling a meeting. Product requirement documents (PRDs) define the user problem, intended outcome, and constraints. Design documents make architectural boundaries, tradeoffs, failure modes, migrations, and rollouts explicit. People read and challenge the thinking asynchronously; once the context is shared, a short in-office discussion or whiteboard session usually resolves the remaining questions quickly.

- We optimize for leverage. Engineers choose the AI tools that work for them, supported by clear ticket context, focused branches, automated tests, and AI review before human review. We also invest in observability, migration tooling, automated recovery, and runbooks so recurring product maintenance does not depend on someone remembering a manual step.

- The engineer who ships a change owns it in production. If something breaks, you lead the fix.

YOU MIGHT BE A FIT IF

- You have designed and shipped production interfaces in React, Next.js, and Tailwind CSS.

- You use Figma when useful, but prefer testing important design decisions in working software.

- You can take an ambiguous problem through user flows, information architecture, interaction design, visual execution, and production code.

- You have enough full-stack familiarity to handle backend work when the experience requires it.

- You understand complex business-to-business software, either through professional experience or strong related portfolio work.

- You have a…