Member of Technical Staff - Post-Training

Ghost; San Francisco (CA); In loco; USD 180.000 - 240.000; Tempo pieno

Descrizione del lavoro

Ghost is seeking a specialist to advance post-training language models that run locally on Core hardware. You will post-train models, develop reinforcement learning methods, and shape on-device agent behavior with an emphasis on latency and privacy.

You should have strong Python and PyTorch skills, with experience building training pipelines, datasets, and evaluations, and be comfortable working on-site in San Francisco with cross-functional teams.

Competenze

• Experience post-training language models with supervised fine-tuning, reinforcement learning, or preference optimization.
• Strong Python and PyTorch skills, with 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 the challenges of training against task outcomes.
• Strong experimental judgment: you can diagnose failures, test hypotheses, and distinguish benchmark gains from meaningful product improvements.
• Ability to work on-site in San Francisco.

Mansioni

• 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 that translate model capability into useful product behavior.
• Build evaluations that measure task completion, personalization, and when agents should act or ask for guidance.
• Work closely with the agent and inference teams to improve quality within on-device memory, compute, and latency constraints.

Conoscenze

Python

PyTorch

On-device inference

Strumenti

PyTorch

Descrizione del lavoro

About Ghost

Ghost is a personal AI hardware company.

To realize the full benefit of what models will do for people, we believe an entirely new platform will be built around AI. Some devices will let your AI understand what is happening around you, others will enable you to get things done without navigating apps or menus.

As these systems become more capable and more personal, it matters who owns them. We’re building a future where that intelligence belongs to you, with an ecosystem of devices and software that gives you greater control over your time, attention, and the things you want to accomplish.

What you'll 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 that translate model capability into useful product behavior.

• Build evaluations that measure task completion, personalization, and when agents should act or ask for guidance.

• Work closely with the agent and inference teams to improve quality within on-device memory, compute, and latency constraints.

Who you are

• Experience post-training language models through supervised fine-tuning, reinforcement learning, or preference optimization.

• Strong Python and PyTorch skills, with 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 the challenges of training against task outcomes.

• Strong experimental judgment: you can diagnose failures, test hypotheses, and distinguish benchmark gains from meaningful product improvements.

• Ability to work on-site in San Francisco.