Agent Engineer
Twin So
Posted: July 17, 2025
Interested in this position?
Create a free account to apply with AI-powered matching
Quick Summary
We are looking for an Agent Engineer to build and maintain a scalable and reliable autonomous agent infrastructure for our clients, with a focus on high-quality and efficient operations.
Required Skills
Job Description
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 vertical agent team
Vertical agents are specialized agents built and trained by Twin to fully automate high value and high scale use cases - like Invoice Operator solving a decade long pain of collecting and reconciling supplier invoices.
The team acts as an independent team focused on identifying high value use cases with our customers, build state-of-the-art agents leveraging our core platform, and deploy them to production.
About the position
Main challenges
Responsible for working with enterprise customers from discovery to production deployment
The role entails working with customers to discover, spec and implement these use cases, test them and give customers visibility on the reability of the workflows, improve the accuracy by diagnosing and solving problems, and follow-up to ensure a successful agent that works reliably in production.
The objective of the team is to produce the most performing agents (reliability, speed, cost) on the market for the identified use cases.
Daily tasks
You'll be leading the development of high scale, flagship agents, that we expect to reach millions to tens of millions of ARR in the next years. To do so, you will have to mix very pragmatic and logical reasoning, excellent understanding of the use cases, and a deep mastery of the agent technical stack.
• Discuss use cases with customers and spec workflows
• Interact with engineering team to prioritize new features
• Write and iterate on prompts and function tool calls
• Set up the evaluation and testing environment and conditions for vertical agents
• Diagnose problems and continually increase the agent accuracy
• Evaluate new agents and models on the use case
• Work with fullstack engineers on custom frontends and tools
• Follow up and give customer visibility on agent success
Requirements
• Experience with large language models and agentic workflows
• Experience with enterprise customers
• Proficiency in Typescript
• Some knowledge of Rust
• High agency and hardcore work culture