Job description for AI Product Engineer at Actionbook
About Us
We're Actionbook — we let AI agents operate any website. People already use agents like Claude and ChatGPT to think; Actionbook gives them a fast, reliable way to act: research behind logins, fill forms, click through real sites, and handle repetitive tasks — all inside the user's own browser, with the user in control.
We're not building another agent. We're the tool your agent uses to get things done on the web — works with any MCP client.
We're an early-stage startup in Singapore. A small team, AI-first, ships fast.
About the Role
You're one of our first product engineers — the person who turns our infrastructure into something people reach every day. The interfaces, flows, and controls that make agents feel safe, fast, and worth pointing at real work.
You'll work directly with the founding team and own product surfaces end-to-end: decide what to build, ship it, watch how people use it, change it. We care about agency, taste, and shipping more than any one credential. You should love writing code and obsess over how it feels to use.
This is a foundational hire. The way the product looks and feels in a year is going to be your fingerprint as much as anyone's.
Fresh grads welcome — what you've shipped matters more than how long you've been at it.
What You'll Work On
• Build user-facing product features end-to-end with TypeScript, React (Next), and APIs.
• Design the flows users actually live in, and make them clean and obvious.
• Prototype new ideas, ship the best ones, kill the rest.
• Pair with the founding team on roadmap, recruiting, and how we sell what we build.
You Might Be Fit If
• You've shipped things real users have actually used — side projects, internships, hackathons, prior roles, whatever. We'll ask to see them.
• Strong full-stack with TypeScript and React. Comfortable end-to-end: backend, frontend, basic infra.
• You work with AI coding tools natively — Claude Code, Codex, opencode — and ship faster because of them, not around them.
• Taste. You notice when something's clunky and it bugs you until it's fixed.
• You can walk through what you built, what worked, and what you'd do differently.
• 0–2 years of full-time experience (or equivalent intensity from school, hackathons, OSS, multiple internships). Fresh grads with a strong portfolio: encouraged.
Nice to Have
• Strong design sense — Figma, design systems, product prototyping.
• Experience with agent loops, tool-calling, RAG, or LLM-powered features.
• Familiarity with browser automation, Playwright, Chrome extensions, or computer-use agents.
• Open-source projects with traction, public demos, or technical writing people read.
Details
• Location: Singapore, onsite.
• Hours: Full-time, 5 days/week.
• Compensation: S$6,000–10,000 per month (final number based on level and what you bring).
• Equity: Meaningful early-stage stock options — specifics discussed at offer stage.
• Benefits: Discussed at offer stage.
• Start date: Rolling — we want you yesterday.
How to Apply
Apply through Glints with your resume and one project you're proud of. Optional: a demo video, writeup, or a short note on an AI workflow you think should exist.
