About the role
We’re hiring a Founding Engineer to help build Castari into the default platform for deploying and running agentic apps, starting with Claude Agent SDK.
This role is about shaping the product and the company as much as writing code. You’ll help define what the “Vercel experience” should look like for agents, make foundational technical decisions, and ship the first versions that users actually depend on.
What you’ll do
- Build core platform capabilities that make agent deployment feel simple and trustworthy
- Turn early user pain into clear product primitives and fast iterations
- Make architectural decisions that hold up as we scale from early adopters to serious production workloads
- Help establish engineering culture: speed, quality, security instincts, and taste
What we’re looking for
- You can build end-to-end systems and keep them clean
- You care about developer experience and product clarity, not just infrastructure
- You have strong judgment around tradeoffs (speed vs correctness, abstraction vs simplicity)
- You want ownership and impact more than narrowly scoped work
Who you are
- You’re the kind of engineer who sees ambiguity and turns it into momentum
- You’re comfortable owning a problem from “what should this be?” to “it’s shipped and people rely on it”
- You write code with good taste: simple, readable, and hard to break
- You communicate clearly, move quickly, and don’t need a lot of process to execute
- You’re excited to work close to users and let real usage shape the product
Bonus
- You’ve built developer tooling people love (CLIs, SDKs, frameworks, platforms)
- You’ve worked on infrastructure where security boundaries matter (sandboxes, containers, isolation, multi-tenant systems)
- You’ve built or operated systems with real reliability requirements (queues, retries, timeouts, idempotency, incident response)
- You’ve implemented observability that actually helps debug production behavior (structured logs, traces, event streams)
- You’ve built with or around LLM/agent systems and have opinions on how this ecosystem should evolve
Why this is interesting
If you believe agents are the next major application platform shift, then the deployment layer becomes a default winner-take-most surface. We’re early enough that the “right” platform doesn’t exist yet, and small teams can still define it.
About Castari
Castari is building the deployment platform for AI agents, the way Vercel became the default for web apps.
The world is shifting from “prompting a model” to shipping autonomous software. Agents will run real workflows: pulling data, browsing, generating files, calling tools, and coordinating multi-step tasks. That’s a massive new surface area for reliability, security, and operations.
Right now, most agent teams are duct-taping together infrastructure that was never designed for this. The result is predictable: fragile deployments, unclear failure modes, unsafe execution, and almost no visibility into what happened when an agent goes off the rails.
Castari’s long-term goal is to be the go-to runtime and control plane for agentic applications. A place where teams can deploy agents with confidence, run them safely, observe everything, and scale without rebuilding their stack every time the agent gets more capable.
We’re starting with a deliberate wedge: Claude Agent SDK. Our goal is simple: when you build an agent with the Claude Agent SDK, Castari should be the obvious place to deploy it.
Required skills
Job details
Salary
$120,000 - $200,000
Equity
1% - 3%
Location
Remote
Experience
3+ years
Funding
Total raised
$500K
Last stage
Pre-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.