Agent Engineer, Luna
At monday.com · Tel Aviv; Tel Aviv, Israel
- Engineering
- Full-time
See how well you match Match me reads your CV and picks the jobs that suit you best.
Get jobs like this within hours Radar emails you new jobs open to you within hours of us finding them, before most people see them.
Where you’ll work
Hybrid, based in Tel Aviv
“Tel Aviv”
From the location.
“Tel Aviv, Tel Aviv, Israel”
From the job board field.
The job board lists it as hybrid.
Hybrid means some days in the office. The listing says how many, and where.
Report a mistake
- Posted
- 8 September 2026
- First seen by us
- 3 November 2026
- Last checked
- 13 hours ago
Job description
From monday.com’s job post, as they wrote it.
Luna is a new startup inside monday.com Agent Labs, founded and run by monday.com's CEO, the program that spins up independent startups from scratch. Each one runs like a seed-stage company: a tiny team, a real product, real users, with monday.com's backing and distribution.
Luna already has a live product, a pile of open problems nobody has answered yet, and no layers between you and the person making the calls. We're hiring the engineer who builds it. You work directly with the founder, monday.com's CEO. Decisions happen in the conversation, not in a roadmap review. You own the engineering. The founder owns the product.
Read the full description
What we're building
Meet Luna, the first generation of autonomous agents, which proved that agents can do real work. It also proved they broke. Unbounded self-coding that can touch any key. Everything is riding on raw LLM reasoning, so execution drifts. No way to see what actually happened.
Luna is the second generation. It still learns and improves itself, but on a scaffold built for trust:
* Deterministic workflows, the agent writes and refines, then runs on a real engine instead of re-reasoning every time.
* A one-way vault. Secrets resolve below the plugin layer and never enter the model's context.
* Rollback on every change, an audit trail on every action, and approval gates on anything sensitive.
* Everything else is a plugin: tools, channels, skills, isolated per agent.
Luna isn't a chatbot. You describe the goal, it builds the workflow, you correct it, and it runs reliably next time. A private Luna spins up in about a minute today.
There's no playbook yet for what a good agent is in this context. We're writing it with real use cases and real constraints. That's the job.
Who we're looking for
* An experienced builder at heart. You'd rather ship the thing than pitch it. This is an engineering role, not a founder track.
* Instincts about agents. Before writing a line, you ask what the model must never be allowed to touch, how you'd know it failed, and what happens when it does. Shipping ten agents isn't required. Having thought hard about one is.
* Independent. Hand you something vague, and you come back with something that works.
* Strong fundamentals in distributed systems and reliability, with production experience.
* Nice-to-have: LLM tooling in production, tool use, sandboxing, and evals. A security-minded way of building.
*
Agent Engineer, Lunamonday.com
Apply on monday.com (opens in a new tab)Get jobs like this by email
Once a week, we email the new remote jobs open where you live, each with the line that proves it. Every email has a one-click unsubscribe.
