source-url: https://cruxevals.com/careers/senior-researcher-july-2026/
apply-url: https://forms.gle/RpVS7ptvisvZipNA6
CRUX, a research organization focused on updating AI expectations, is hiring a Senior Researcher to co-lead open-world evaluations of frontier AI agents. This full-time, remote position offers a salary range of $150,000-$220,000 per year and requires a strong track record of driving ambitious research projects. The ideal candidate will have around 5+ years of experience in a related field.
Overview
CRUX conducts open-world evaluations, including autonomous iOS app development and AI R&D automation, to shape the research agenda for AI expectations. The Senior Researcher will work closely with software engineers to design and deliver published results on a regular cadence.
- Long-horizon tasks in real-world environments
- Autonomous iOS app development and publication
- AI R&D automation
Role & Responsibilities
The Senior Researcher will be responsible for designing new open-world evaluations, planning and overseeing evaluation runs, analyzing agent logs and trajectories, and leading report writing and public write-ups.
- Design new open-world evaluations in domains such as AI R&D, software engineering, and novel game playing
- Analyze agent logs and trajectories to characterize how agents succeed and fail
- Lead report writing and public write-ups on a publication cycle of roughly one to two months
Requirements
- A track record of independently driving ambitious technical or empirical research projects
- Strong engineering skills, including proficiency in Python and hands-on experience with LLM agents and scaffolds
- Sound research judgment and the ability to assess ML papers or agent research outputs
- Clear, efficient writing for both expert and public audiences
Compensation & Benefits
- Salary: $150,000-$220,000 per year, depending on experience
How to Apply
To apply for this role, candidates should submit their application through the provided URL. The application process is expected to be highly competitive, and only shortlisted candidates will be contacted for further evaluation.
- Submit application through the provided URL
- Ensure all required documents and information are included in the application
Who Should Apply
This role is ideal for experienced researchers who can drive ambitious projects independently and have a strong track record of delivering research on short timelines. Candidates with a PhD are not required, but demonstrated work and strong engineering skills are essential. The role offers substantial independence in setting direction and working closely with software engineers.
The successful candidate will have a unique blend of technical and research skills, with the ability to communicate complex ideas to both expert and public audiences. They will be able to work effectively in a remote environment and prioritize tasks to meet deadlines.
Frequently Asked Questions
What is the salary range for this role?
The salary range for this role is $150,000-$220,000 per year, depending on experience.
Is a PhD required for this role?
No, a PhD is not required for this role. Demonstrated work and strong engineering skills are more important than credentials.
What are the key responsibilities of this role?
The key responsibilities of this role include designing new open-world evaluations, planning and overseeing evaluation runs, analyzing agent logs and trajectories, and leading report writing and public write-ups.
Can I apply for this role if I don't have experience with LLM agents and scaffolds?
While experience with LLM agents and scaffolds is desirable, it is not essential. Candidates with strong engineering skills and a willingness to learn can still apply for this role.
Is this role full-time or part-time?
This role is full-time and remote, offering flexibility and independence in setting direction.
How do I submit my application?
To submit your application, please use the provided URL and ensure all required documents and information are included.