Senior AI Safety Researcher (Evaluation of AI safety schemes) Montreal

LawZero; Montreal; On-site; CAD 90,000 - 130,000; Full time

Job summary

Join a leading organization focused on AI safety as a Senior AI Safety Researcher. This role involves analyzing safety schemes and evaluating AI systems to ensure alignment with human values. Contribute to impactful research while collaborating with experts in a vibrant work environment.

Benefits

20 days vacation per year

Employer contribution to retirement savings

Generous flexible benefits

Qualifications

• 3+ years of experience in AI safety research or related fields.
• Ability to explain complex ideas to diverse audiences.
• Demonstrated ability to reason about fundamental AI safety issues.

Responsibilities

• Analyze and evaluate various AI safety schemes.
• Discover and investigate AI safety failure modes.
• Guide theoretical work to answer safety questions.

Skills

Mathematical analysis

Communication

Analytical thinking

Problem-solving

Education

Advanced degree in Computer Science, Mathematics, or Physics

Job description

Senior AI Safety Researcher (Evaluation of AI safety schemes)

Montreal

We are seeking a Senior AI Safety Researcher to join our team working on a novel AI safety research agenda. In this role, you will think about challenges and solutions related to complex topics in AI safety to ensure that AI systems behave reliably, predictably, and in alignment with human values and intentions, even as they become increasingly capable and autonomous.

Key responsibilities

• Analyze and evaluate various AI safety schemes, with a focus on guaranteed safe AI approaches at the system level.
• Discover and investigate failure modes, implicit assumptions, and tradeoffs in proposed safety plans.
• Detect when changes in approaches alter implicit assumptions.
• Detect when safety arguments assume the desired property they aim to establish.
• Develop rigorous arguments to validate or invalidate safety approaches, ideally general arguments that apply to whole classes of safety approaches.
• Guide and prioritize theoretical work to answer critical safety questions efficiently.
• Communicate complex findings effectively to various stakeholders, including both AI safety experts and non-experts.

Skills and qualifications

• Advanced degree in a relevant field (e.g., Computer Science, Mathematics, Physics). A PhD is preferred but not required if the candidate demonstrates exceptional abilities.
• 3+ years of experience in AI safety research or related fields, or demonstrated abilities equivalent to this level of experience.
• Strong mathematical background, with the ability to quickly learn and apply concepts from various disciplines.
• Strong communication skills, with the ability to explain complex ideas to diverse audiences.
• Excellent analytical and problem-solving skills, with a demonstrated ability to think critically about complex systems and identify critical and often overlooked considerations in AI safety.
• Demonstrated ability to reason about fundamental AI safety issues beyond specific scenarios, encompassing agency, goal-directedness, and the potential for seemingly benign behaviors that can lead to catastrophic outcomes at scale.
• Track record of contributing to high-quality research in AI safety or related fields.
• Ability to work collaboratively in a team environment while also being self-motivated and independent.
• Ability to identify and implement key safety features in AI architectures to mitigate risks during gradual capability increases.

What we offer

• The opportunity to contribute to a unique mission with a major impact.
• A minimum of 20 days vacation per year upon start.
• A minimum retirement savings employer contribution of 4%.
• Generous flexible benefits designed to contribute to your well-being.
• A team of passionate experts in their field.
• A collaborative and inclusive work environment with offices in the heart of Little Italy, in the trendy Mile-Ex district, close to public transportation.

About LawZero

LawZero is a non-profit organization committed to advancing research and creating technical solutions that enable safe-by-design AI systems. Its scientific direction is based on new research and methods proposed by Professor Yoshua Bengio, the most cited AI researcher in the world. Based in Montreal, LawZero’s research aims to build non-agentic AI that could be used to accelerate scientific discovery, to provide oversight for agentic AI systems, and to advance the understanding of AI risks and how to avoid them. LawZero believes that AI should be cultivated as a global public good—developed and used safely towards human flourishing. For more information, visit www.lawzero.org

You belong here

At LawZero, diversity is important to us. We value a work environment that is fair, open and respectful of differences. We welcome applications from highly qualified individuals interested in working towards our mission in a respectful, inclusive and collaborative setting.

Your personal information will be collected and processed by LawZero to evaluate your application for employment in compliance with ourPrivacy Policy . Under privacy laws in force in your country of residence, you may have several privacy rights, such as to request access to your personal information or to request that your personal information be rectified or erased. Details on how you can exercise your rights can be found in our Privacy Policy.

Apply for this job

*

indicates a required field

First Name *

Last Name *

Preferred First Name

Email *

Phone

Resume/CV *

Enter manually

Accepted file types: pdf, doc, docx, txt, rtf

Enter manually

Accepted file types: pdf, doc, docx, txt, rtf

Are you legally entitled to work in Canada? * Select...

As part of this recruitment process, you will be required to undergo background checks. Do you wish to proceed? * Select...

Which topic related to AI safety is currently most interesting to you?

LinkedIn profile

By checking this box, I agree to allow LawZero to store and process my data for the purpose of considering my eligibility regarding my current application for employment. *

By checking this box, I agree to allow LawZero to retain my data for future opportunities for employment for up to 900 days after the conclusion of consideration of my current application for employment.