Agent Engineer, Luna
Monday.comWork Management company
Tel Aviv, IsraelSenior
Sapphire Ventures
Hamilton Lane
HarbourVest Partners
ION Crossover Partners
Vintage Investment Partners
Genesis Partners
Data & AINew
About the role
TL;DR
Build and engineer the next generation of autonomous agents for Luna.
- •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.
- •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.
- •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.
- •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.
Required skills
LLMsPythonLangChainREST APIGitLinux
Nice-to-have skills
OpenAI APIAnthropic APIGemini API
Domain expertise
aiproductivity
Tech stack
PythonLLMsOpenAI APIAnthropic APIGemini APILangChainGitLinuxREST API
