Applied RL Engineer: From Discovery to Deployment

Prime Intellect, Inc.; United States; A distancia; USD 140.000 - 190.000; Jornada completa

Descripción de la vacante

Prime Intellect, Inc. is building an open superintelligence stack for frontier-scale post-training of AI models. We seek builders who work across research, infrastructure, and go-to-market to deploy impactful RL solutions.

You will own the end-to-end RL lifecycle, from problem framing with customers to deploying improvements on live systems. You will collaborate directly with customer researchers, engineers, and leaders, applying rigorous experimentation and leveraging Prime's shared stack to

Formación

• Proficiency in Python and RL/post-training workflows.
• Strong experimental judgment for evaluating RL experiments.

Responsabilidades

• Own applied RL programs from problem framing to deployed improvement.
• Collaborate with customer researchers, engineers, and leaders to deliver outcomes.

Conocimientos

Python

Reinforcement Learning

Agent systems

Experimental judgment

Ambiguity handling

Descripción del empleo

Prime Intellect, Inc. is building an open superintelligence stack for frontier-scale post-training of AI models. We seek builders who work across research, infrastructure, and go-to-market to deploy impactful RL solutions.

You will own the end-to-end RL lifecycle, from problem framing with customers to deploying improvements on live systems. You will collaborate directly with customer researchers, engineers, and leaders, applying rigorous experimentation and leveraging Prime's shared stack to