Wordware is an IDE for building AI agents using natural language.

It looks and feels like Notion, but lets you design, test, and deploy AI systems in real time - without writing code.

Our mission is to bring structure and joy to human–AI collaboration.

We’re building a generational company that empowers the next billion knowledge workers to create with AI - not by writing code, but by expressing intent.

We’re backed by Spark Capital, Felicis, and Y Combinator ($30M seed round - the largest in YC history).

We work hard, move fast, and don’t take ourselves too seriously. It’s intense, but it’s also fun - at Wordware, you’ll do the best work of your life alongside people you genuinely like.

what’s it going to be like

in Shackleton's famous words: “people wanted for hazardous journey. low wages, bitter cold, long hours of complete darkness. safe return doubtful. honour and recognition in the event of success.”

risk + excitement + hard work = startup life

sure, you could join a big company and make big money, but there's something about that constant thrill of hope, that addictive energy that makes us keep coming back to startups 😵‍💫

to thrive here, you need to embrace our delulu universe, where victories give us hope and failures make us want it even more. yes, it can be intense, but you'll have direct impact on everything we build.

you're ready to roll up your sleeves, identify your own features to build and find your own problems to solve? grab a beer and a slice of pizza. let's build the future of AI development together.

who thrives here:

we're not just looking for technical skills. we need people who push limits in life, whether that's:

• skiing down a gnarly double black diamond
• speaking in front of crowds
• starting companies
• pushing through fear
• tackling impossible problems

building a company trying to define a market takes a certain type of person:

• you stay cool when everything's on fire
• you take smart risks (and learn from dumb ones)
• you adapt fast when plans explode
• you have the grit to power through setbacks
• you see obstacles as puzzles to solve

if you've ever looked at something terrifying and the first thought that comes is "LFG" - we should talk. at wordware, we're redefining how the world builds with ai. it's scary, exciting, and we are delusional

p.s. yes we have crossbow competitions and do sauna+cold plunges in the sea together

don't see your role? apply anyway

tl;dr if you're exceptional, we'll create a role for you. simple as that.

how to stand out:

• build something cool with wordware and, even better, join our discord server to show us
• show us how to improve our product before we even talk
• prove you're proactive (we're really busy!)

if you're truly excellent, just drop your linkedin to lucy [at] wordware.ai

ps: seriously, if you're great at what you do but don't fit the roles above, reach out anyway. we're always looking for exceptional people who get what we're building.

pps: we judge you on what you build, not when you build it. weekends are sacred, burnout is stupid. we're looking for people who want to create something generational and know when to push hard and when to recharge.

⚠️ Please read first

• This is a full-time, in-person role based in San Francisco (Presidio) - we work from the office 5 days a week.

• You must be based in the Bay Area or willing to relocate before starting.

• We require US work authorisation , but are open to O-1 visa sponsorship for truly exceptional candidates.

About Wordware

Wordware is an IDE for building AI agents using natural language.

It looks and feels like Notion, but lets you design, test, and deploy AI systems in real time - without writing code.

Our mission is to bring structure and joy to human–AI collaboration.

We’re building a generational company that empowers the next billion knowledge workers to create with AI - not by writing code, but by expressing intent.

We’re backed by Spark Capital, Felicis, and Y Combinator ($30M seed round - the largest in YC history).

We work hard, move fast, and don’t take ourselves too seriously. It’s intense, but it’s also fun - at Wordware, you’ll do the best work of your life alongside people you genuinely like.

What You’ll Do

As an Applied AI Engineer , you’ll be responsible for building, refining, and scaling the agent systems inside Wordware — from architecture to evals to deployment.

This isn’t a research role. We care about what works in production: fast response times, predictable behavior, traceability, and uptime.

You’ll work across the stack — with infra, frontend, and product — to make sure the agents users build inside Wordware are robust, useful, and usable.

A few examples of what you might work on:

• Implement multi-step, tool-using agents that hit real APIs and handle retries, auth, timeouts, and edge cases.

• Build RAG pipelines that support grounded answers from structured and unstructured sources.

• Design agent memory systems that persist relevant state across runs — e.g. scratchpads, summary buffers, embedding stores.

• Add determinism + replay to agents so users can trace and debug behaviors step by step.

• Own and evolve our eval framework — both automated checks and human-in-the-loop scoring.

• ${your ideas}.

Who You Are

Minimum

• 3+ years of engineering experience , including time shipping production software.

• You've built and deployed agent-like systems — multi-step LLM pipelines, tool-using bots, scripted assistants, or similar.

• Hands-on experience with:

• You write production-grade code and can work across systems without needing a spec.

• You thrive in fast-paced, product-first environments where the goal is shipping.

Bonus (not required)

• Experience with frameworks like LangChain , CrewAI , or DSPy — or strong opinions about why you don’t use them.

• Shipped agents that are live in the wild — used by customers, not just internal demos.

• Familiarity with LLM ops , tracing, observability, and failure handling.

• You’ve been a founder or early engineer and care deeply about product quality.

The Process

We keep our process simple. Exceptional candidates go from first touch to offer within  2 weeks.

1. Application

2. 15-min intro call

3. 45-minute technical interview

4. System design interview

5. Final conversation

6. Work trial

• Full-stack Typescript, Next.js, React and SST serverless on AWS/Cloudflare
• Using TipTap as the core of our IDE with Y.js for collaboration
• PartyKit (Cloudflare Durable Objects) for Y.js websockets and likely for future orchestration of pipelines
• Open source LLMs hosted by Together AI (we’re a customer story on their website) + Groq + OpenAI/Anthropic/Mistral/Google/Cohere/Perplexity for proprietary LLMs