Multi-Agent Infrastructure Engineer
About the role
We are looking for a strong, broadly capable engineer to build infrastructure for AI agents: stateful memory and execution harnesses, tool and plugin systems, checkpointing, multiple isolated "worlds," and interactions among many agents. This work also requires the supporting backend, model-serving, observability, evaluation, and production infrastructure that keeps those systems reliable. The central requirement is practical experience building and orchestrating AI agents, preferably multi-agent systems. We need someone who can design flexible systems for rapid research iteration while keeping their interfaces crisp, their execution efficient and low-latency, and their foundations dependable enough for increasingly deployed use.
About Prior Computers
Prior Computers, Inc. is an early-stage AI startup that describes itself as 'the machine psychology company,' focused on making AI system behavior understandable, predictable, and controllable from training to deployment. The company is an MIT spinout based in Cambridge, MA, working on interpretability, internal representations, and safety for modern foundation models. Their technical work includes research on world representations and how multi-task training shapes internal model structure.
Other roles at Prior Computers
Refer someone
Know someone great for this role?
Share your link. If they get hired through Standout, you get $3,000.
Job details
Salary
$200,000 - $400,000
Equity
0.1% - 1%
Location
San Francisco, CA
Experience
4+ years
Funding
Total raised
$20M
Last stage
Seed
Investors
What happens next.
No applications, no recruiter spam. Just the intro.
Confirm the fit
A few questions to make sure this role is the right shape for you. Two minutes.
I pitch you to the company
I write the intro, send it to the founder, and handle the back-and-forth.
A meeting lands on your calendar
If they’re a yes, I book the chat. You show up — that’s the whole job-hunt.