Twin is building fully autonomous AI agents that run real business operations.
You give a goal.
Twin figures out the steps.
It executes them end-to-end, via APIs when they exist, via the browser when they don’t and produces real deliverables.
Not prompts. Not workflows. Not chatbots.
Autonomous systems that operate reliably over time.
While most AI tools stop at generating text or code, Twin automates the operational backbone of companies: growth, support, finance, reporting, logistics, the work that actually keeps businesses alive.
Twin is built by a small, senior team of repeat founders and engineers in Paris.
Founded by Hugo Mercier (ex-Dreem, $60M raised, 150+ employees, acquired) and João Justi (high-performance systems, cryptography at Zama, compilers, VMs, ML systems).
$10M seed. Backed by LocalGlobe.
We are building core infrastructure for autonomous companies and we are doing it with a small, elite team.
If you’re looking for comfort, process, and predefined specs, this is not it.
If you want to build systems that operate at scale and redefine how companies run, keep reading.
As part of the team, you will be responsible for the design and implementation of the agent engine features, and will contribute to solving some of the toughest challenges in agent performance.
Optimised, low-latency browser interaction between user and remote browser
Efficient and reliable communication and management of the browser through a low-level communication protocol
Building a reliable architecture for large-scale task automation, resistant to failures
Managing efficient communication between the different parts in a reliable and efficient way
Building both agent-facing and user-facing features
Experience shipping production-level Rust code
Interest in working across the full stack and knowing all the parts of the system
Familiar with basic LLM concepts
High agency and hardcore work culture