Applied RL Engineer - Chip Design and Post-Training Systems

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

Descripción de la vacante

Prime Intellect is seeking a researcher specializing in reinforcement learning for chip design. You will develop agentic RL methods, design long-horizon experiments, and translate workflows into reusable tasks, environments, and reward signals.

You will collaborate with users and research partners to advance semiconductor workflows, building Python artifacts that others can run, inspect, and extend, while contributing to the open superintelligence stack.

Formación

• Depth in RL, agents, or post-training methods.
• Fluent in semiconductor workflows and domain knowledge.

Responsabilidades

• Turn workflows into tasks, environments, and reward signals, run post-training experiments against baselines.
• Work directly with users and research partners while maintaining a research agenda.

Conocimientos

RL expertise

Python programming

Semiconductor workflows

Descripción del empleo

Prime Intellect is seeking a researcher specializing in reinforcement learning for chip design. You will develop agentic RL methods, design long-horizon experiments, and translate workflows into reusable tasks, environments, and reward signals.

You will collaborate with users and research partners to advance semiconductor workflows, building Python artifacts that others can run, inspect, and extend, while contributing to the open superintelligence stack.