Member of Technical Staff - Post-Training

The role

You will post-train open models to power personal agents that run locally on Core. You will develop supervised fine-tuning and reinforcement learning methods and build evaluations to measure task completion.

What you will do

• Post-train open models to power personal agents that run locally on Core.
• Improve tool use, reasoning, and reliable execution across complex, multi-step tasks.
• Build training datasets and feedback pipelines grounded in realistic agent workflows.
• Develop supervised fine-tuning and reinforcement learning methods.
• Build evaluations that measure task completion, personalization, and agent guidance.
• Work with agent and inference teams to improve quality within on-device constraints.

Required qualifications

• Experience post-training language models through supervised fine-tuning, reinforcement learning, or preference optimization.
• Strong Python and PyTorch skills.
• Experience building and debugging training pipelines.
• Experience creating datasets and evaluations that produce measurable improvements in model behavior.
• Familiarity with tool-using agents, multi-step environments, and training against task outcomes.
• Strong experimental judgment to diagnose failures, test hypotheses, and distinguish benchmark gains.

About the company

Ghost is a personal AI hardware company. They are building an ecosystem of devices and software to give users control over their intelligence.