Software Engineer — Platform

Tasklet is building the cloud agent OS for knowledge work. Instead of switching between dozens of SaaS apps, our users connect one AI agent to all their tools and let it handle their work — pulling data, taking actions, generating UIs on the fly, and running 24/7 in the cloud.

We've raised $29.5M from Union Square Ventures, Lightspeed, Y Combinator, Jeff Dean, and Patrick & John Collison. Our team of 9 in San Francisco is led by Andrew Lee (founded Firebase, sold to Google) and Jonny Dimond, and includes engineers from Google, Amazon, and OpenAI.

We're growing fast, shipping constantly, and competing directly with the AI labs to build the agent platform that replaces legacy application software. Nearly every line of code here is written with AI — we're an engineer-driven team that believes deeply in giving models more agency and using them to multiply what a small team can do.

Do not apply through this platform. To apply, you must submit a short video by email. See the full application instructions at https://tasklet.ai/careers.

Tasklet is building the AI platform companies use to run their business on agents. A customer describes an outcome in plain English, and Tasklet gets the work done across their tools and systems—immediately or in the cloud 24×7. We’re looking for unusually strong generalist engineers to build the product foundations that make Tasklet work. This includes the backend APIs behind product features; accounts, workspaces, permissions, billing, payments, and analytics; and the connector, authentication, webhook, and trigger infrastructure that lets Tasklet act across a company’s tools. This is a mostly backend role, but not a narrow specialization. You’ll turn messy product and business needs into clean primitives, then follow those systems into the product and infrastructure as needed. We care more about intelligence, first-principles reasoning, and strong computer-science fundamentals than experience with any particular technology or domain. We’re open to candidates from mid-level to Staff+. Regardless of level, this is a hands-on IC role: everyone at Tasklet personally builds and ships.

$225K–$425K base salary

0.20%–0.65% equity

Compensation is calibrated to experience and expected impact. Competitive benefits include medical, dental, vision, 401(k), four weeks of PTO, free lunch, and more.

• Build backend APIs and services that power Tasklet’s product.
• Develop core systems for identity, workspaces, sharing, permissions, billing, payments, and analytics.
• Build reliable infrastructure for connectors, authentication, webhooks, triggers, and third-party integrations.
• Design simple abstractions and data models that can support a fast-changing product.
• Own systems in production and improve their correctness, security, reliability, and operational simplicity.
• Work across the stack and across role boundaries whenever that is the best way to solve the problem.

• You’re an exceptional problem solver with strong computer-science fundamentals.
• You reason from first principles, see how parts interact within a larger system, and move comfortably between levels of abstraction.
• You’ve built and operated meaningful production software, and you can debug a problem wherever it leads.
• You balance clean design with pragmatism: you know when to create a durable primitive and when to ship the simple thing.
• You learn quickly, operate well with ambiguity, and prefer responsibility over process.
• You use AI deeply in your own work. We don’t require prior professional AI experience, but we do expect you to already be seriously engaged: using current models, probing their limits, and forming your own views about where they are going. This role is full-time and primarily in person at our office at 1 Post St. in San Francisco.

We're solving some of the hardest problems in applied AI agents.

Some of our core technical challenges include:

• building a cloud-native agent runtime that reliably orchestrates long-running, multi-step tasks across thousands of third-party APIs and MCP servers
• context engineering that keeps agents sharp and token-efficient while juggling rich tool sets, user memory, and multi-turn conversations
• a connections layer that lets agents reason intelligently across every tool a user has wired up
• on-the-fly UI generation (we call them "instant apps") so agents can produce interactive frontends when a chat response isn't enough
• cloud-based computer use for when agents need a real browser or desktop

We're constantly adapting to stay on the frontier. Nearly every line of code here is written with AI, and we're actively working on closing the loop on recursive self-improvement. We use a modern tech stack for our apps & backend.

The whole process can move very quickly.

1. Send us a video application by following the instructions on our jobs page here.
2. We’ll get on a call with you
3. If there seems like a mutual fit, we’ll bring you onsite for 1/2 day.