Software Engineer, Safety White Hat at OpenAI

San Francisco, California, United States

Apply Now

$255,000 – $405,000Compensation

Senior (5 to 8 years), Expert & Leadership (9+ years)Experience Level

Full TimeJob Type

UnknownVisa

Artificial Intelligence, TechnologyIndustries

Requirements

Proven track record of leading White Hat initiatives for frontier models or complex AI systems
Deep familiarity with LLM behavior, post-training evaluation techniques, and AI safety research
Highly attuned to failure modes in AI systems (e.g., sycophancy, jailbreaking, and harmful outputs) and ability to surface these before production
Preference for working in close proximity to research teams rather than commercial or sales-focused environments
Experience building and scaling high-trust, high-performance technical teams

Responsibilities

Define the strategic direction and methodology for adversarial testing—including empirical probing, stress-testing, and alignment-focused evaluations
Identify and characterize emergent risks in reasoning, instruction-following, agentic behavior, and other critical capabilities before they result in external incidents
Collaborate with external partners to extend the reach and rigor of the White Hat efforts
Operate with a lean and efficient structure, balancing in-house expertise with vendor support where appropriate
Help shape the strategy and vision for ensuring fast and safe deployment of more powerful models and product experiences
Define the scope and methodology of adversarial evaluations
Drive alignment between model development and safety

Skills

LLMs

AI Safety

Adversarial Testing

Post-Training Evaluation

Jailbreaking

AI Alignment

Stress-Testing

Agentic Behavior

Reasoning

Instruction-Following

OpenAI

Develops safe and beneficial AI technologies

About OpenAI

OpenAI develops and deploys artificial intelligence technologies aimed at benefiting humanity. The company creates advanced AI models capable of performing various tasks, such as automating processes and enhancing creativity. OpenAI's products, like Sora, allow users to generate videos from text descriptions, showcasing the versatility of its AI applications. Unlike many competitors, OpenAI operates under a capped profit model, which limits the profits it can make and ensures that excess earnings are redistributed to maximize the social benefits of AI. This commitment to safety and ethical considerations is central to its mission of ensuring that artificial general intelligence (AGI) serves all of humanity.

San Francisco, CaliforniaHeadquarters

2015Year Founded

$18,433.2MTotal Funding

LATE_VCCompany Stage

AI & Machine LearningIndustries

1,001-5,000Employees