Applied AI Researcher — Post-Training Systems & RL

Prime Intellect, Inc.; United States; Remote; USD 180,000 - 260,000; Full time

Job summary

Prime Intellect, Inc. is building the open superintelligence stack for post-training AI in the United States. You will advance RL research, develop agents, and contribute to robust evaluation frameworks.

You will collaborate with partners to tackle ambiguous problems, ship experiments, and iterate on production-ready loops with monitoring and governance. Strong Python skills and sound experimental judgment are essential for success in this role.

Qualifications

• Depth in RL, agents, or post-training systems.
• Strong Python and experimental judgment.
• Comfort owning ambiguous problems with partners.

Responsibilities

• Build quantitative-research environments and agents.
• Design rewards and verifiers for robust out-of-sample behavior.
• Operate production loops with monitoring and human authority.

Skills

RL research

Python

Experimentation

Job description

Prime Intellect, Inc. is building the open superintelligence stack for post-training AI in the United States. You will advance RL research, develop agents, and contribute to robust evaluation frameworks.

You will collaborate with partners to tackle ambiguous problems, ship experiments, and iterate on production-ready loops with monitoring and governance. Strong Python skills and sound experimental judgment are essential for success in this role.