Software Engineer
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Role details
Tech stack
Requirements
Helpful, but not required TypeScript React Bun Effect-TS PostgreSQL Kubernetes AWS
You’re comfortable running multiple AI agents in parallel, and you pick up new things fast.
- You’ve shipped real things end-to-end, multiple times. You owned them.
- You code with AI agents and lean into it, with enough taste to know what’s worth shipping.
- You hold strong technical opinions and change them when the evidence says so.
- You move independently.
-
You want to do the best work of your career.
- You want a true early-stage, in-person experience in San Francisco: fast-paced, high intensity.
About the company
The physical economy only works as a network of interconnected companies, but it still runs on systems that were never designed to talk to each other. Every time two companies need to exchange data, someone builds a custom integration by hand. Business analysts, integration engineers, QA. All manual. Every time. Google EDI if you haven’t. It’s wild.
A lot of companies have tried to fix this. Nobody has. We think AI agents are the way to finally connect the physical economy.
Temper is an agentic integration platform for the real economy. Specialized AI agents handle the full lifecycle: gathering requirements in plain English, generating integration code, testing it, deploying it, and keeping it alive in production. When something breaks, the agents fix it.
We have paying enterprise customers. Real integrations running in production right now. There’s more demand than we can keep up with.
Seed-funded, with over $8M raised. Still an early team, under 10 of us.
These aren’t chatbots or thin wrappers on an LLM. The agents do real work with real consequences in production systems.
Some of what you’d build:
- Agent orchestration across multiple specialized agents coordinating complex workflows
- Platform engineering: basically a mini Vercel for integration runtime with durable execution
- Self-healing systems that detect failures and recover autonomously in production
- A knowledge base of undocumented systems that gets smarter with every integration
Nobody has shipped this kind of platform at production scale yet, even in other verticals.
Grew up in his family’s trucking business. Built the freight product at Hive, Europe’s leading eCom logistics startup, from 0 to $M. Hardware-native engineer who taught himself to code.
Ran 100+ person warehouse operations at Amazon, then consulted on system integrations at KPMG. Built Hive’s largest revenue line from zero.
- Nick (CTO) Built Lilith at 16, led an offensive security program for a nation-state, entrepreneur for 8 years. In eCom, he led the tech that scaled a company from 0 to $100M in 3 years.
- Daniel and Heinrich built Hive from pre-seed to 400+ people. They’ve been living this problem for years.
You’ll own core systems end-to-end: agent platform, infrastructure, integrations runtime. You’ll set the engineering patterns every future hire builds on, work directly with the founders, and ship to production constantly. We need your opinion, not just your code.
Most of the important decisions haven’t been made yet. What you build in the next year shapes the entire system.
Apply for this position
This job is hosted externally. Click below to view the full posting and apply.
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Good distractions
Loading talks and stories from around this role…