About Twin

Twin builds autonomous agents that are reliable and scalable enough for companies to actually delegate work to them.

We engineered the first commercial agent deployed to 500k SMBs—Invoice Operator—achieving 95%+ accuracy at a fraction of the human cost. Over the coming months, we expect this first agent alone to automate millions of man-hours.

To achieve this, we’ve built, among other things:

• A Rust-based browser infrastructure, maintaining low latency at high scale and concurrency.
• A password manager enabling secure and automated agent authentication, including solving 2FA.
• A graph-based agent framework, making complex agents robust through modularity and decoupling.
• A self-correcting infrastructure, allowing agents to learn from mistakes and continuously improve as they encounter new challenges.

Founded in 2024, we’ve raised €12M from LocalGlobe and the founders of companies like Hugging Face, Datadog, and Alan.

Beyond scaling our first agent, our goal is to launch & distribute our next hit agents and ultimately become the trusted layer where autonomous work runs.

About the Core team

The core team is building the foundational blocks of our high-performance, Rust-based agent engine used by agent engineers to build and deploy scalable and reliable vertical agents.

The agent engine encompasses the management of the browser, the communication between browser, agents & humans, the agent framework, the evaluation and testing infrastructure.

The objective of the team is to continuously improve speed, cost, reliability at high scale and concurrency.

About the position

Main challenges

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

Requirements

• 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