Software Engineer - LLM evaluation (Remote)

About the Role

Join an exciting project that pushes the boundaries of AI technology. As a Software Engineer focused on evaluating AI models, you will create detailed and clear guidelines to assess how well AI-generated code works. Your work will help improve the quality and reliability of advanced AI systems used around the world. There is a 15min assessment prior to selection. We anticipate selection to occur within two days of taking the assessment. This role will tentatively begin the week of January 13th 2025.

Currently, we are only accepting applicants from the U.S., UK, and Canada.

Why You’re a Great Fit

You’re an ideal candidate if you:

• Hold a Computer Science degree from a top university in the U.S., Canada, or the UK.
• Have 2+ years of software engineering experience.
• Have exceptional attention to detail.
• Excel in written and verbal communication.

Role Highlights

• Work on a high-impact project contributing to the future of AI.
• Flexible workload: 10–20 hours per week, with potential to increase to 40 hours.
• Fully remote and asynchronous—work on your own schedule.
• Minimum duration: 1–2 months, with potential for extension.

Compensation and Legal Details

• $50–$100/hour, depending on experience, paid weekly via Stripe Connect as a contractor.

About Mercor

Mercor specializes in recruiting experts for top AI labs and is based in San Francisco, CA.
Our investors include Benchmark, General Catalyst, Peter Thiel, Adam D’Angelo, Larry Summers, and Jack Dorsey.

Apply today and make an impact with your expertise!