About the position
As one of our first dedicated product engineers, you will build the core simulation platform: Create a realistic, containerized environment where AI agents perform software engineering and other professional tasks. You will design realistic evaluation scenarios by independently identifying meaningful software engineering tasks, determining clear grading criteria, and selecting the appropriate tools and workflows that allow AI agents to reliably complete tasks. Additionally, you will develop a consumer software product that will serve as a foundation for our simulation platform, where we will task AI agents with building and modifying this product. This will require full stack skills from writing a backend in Python and a frontend with web technologies like React, Typescript, HTML and CSS. You will also establish engineering standards by setting up automated testing, practical CI/CD pipelines, effective monitoring, and clear processes to ensure high-quality code and quick issue resolution. Finally, you will influence technical direction by directly shaping product development, making key architectural decisions, and contributing to growing our engineering team at an early-stage startup.
Responsibilities
- Build the core simulation platform for AI agents.
- Design realistic evaluation scenarios for software engineering tasks.
- Develop a consumer software product as a foundation for the simulation platform.
- Establish engineering standards including automated testing and CI/CD pipelines.
- Influence technical direction and contribute to product development.
Requirements
- Experience building full-stack software products.
- Fluent in TypeScript (React) and Python.
- Comfortable with deployments in Kubernetes-based environments.
- Practical experience with designing CI/CD processes and automated testing strategies.
- Ability to work closely with users to iterate quickly and deliver functional software.
Nice-to-haves
- Experience with container orchestration platforms (Kubernetes).
- Experience with developer tools or internal platforms.
- Experience with reinforcement learning (RL) or machine learning (ML) workflows and infrastructure.
