5 days ago
Berkeley, CA, USA +2 more
Senior / Staff+
H1B Sponsor
Base Salary
$120k - $355k/yr
Responsibilities
- Develop and execute AI benchmarking and safety testing strategies for various AI models and applications.
- Design and implement testing protocols to assess the performance, accuracy, and safety of AI solutions.
- Identify potential risks associated with AI technologies and propose mitigation strategies.
- Collaborate with cross-functional teams to integrate safety measures into AI development processes.
- Analyze testing results and provide detailed reports on AI model performance and safety.
- Stay current with industry standards, regulatory requirements, and best practices for AI safety testing.
- Drive continuous improvement in AI safety testing methodologies and tools.
Requirements
- Bachelor's degree in computer science, Engineering, or related field.
- 8+ years of relevant work experience.
- Expertise with common security testing methodologies.
- Experience with regulatory compliance and industry standards for AI safety.
- Familiarity with AI development frameworks and tools.
- Strong understanding of AI and machine learning algorithms and their associated risks.
- Experience with LLMs, AI Agents, and Natural Language Processing (NLP) techniques, with a focus on safety testing and benchmarking.
- Strong analytical and problem-solving skills.
- Excellent communication and collaboration abilities.
- Detail-oriented individual with a deep drive to research the security of bleeding edge technology.
Benefits
- Equity awards and a generous benefits package including medical, dental, and vision plans.
- Family planning benefits and health savings accounts.
- Flexible spending accounts and transportation savings accounts.
- 401(k) retirement savings plan with company match.
- Life, accident, and disability coverage.
- Business travel accident insurance and employee assistance programs.
- Disability insurance and other well-being benefits.
- 5 days of volunteer time off (VTO) to contribute to the community.
Categories
AI & MLSecurityTesting