1

Interpretability Ai Jobs (NOW HIRING)

Topics could include frontier AI governance, catastrophic and systemic risks, dangerous capability evaluations, model transparency, incident reporting, interpretability, AI-enabled cyber, bio ...

Apply Early

Topics could include frontier AI governance, catastrophic and systemic risks, dangerous capability evaluations, model transparency, incident reporting, interpretability, AI-enabled cyber, bio ...

Researcher, Interpretability

San Francisco, CA ยท On-site

$295K - $445K/yr

About the Team The Interpretability team studies internal representations of deep learning models ... We are particularly interested in applying our understanding to ensure the safety of powerful AI ...

next page

Showing results 1-20

Interpretability Ai information

See salary details

$44.5K

$129.7K

$177.5K

How much do interpretability ai jobs pay per year?

As of Jun 30, 2026, the average yearly pay for interpretability ai in the United States is $129,716.00, according to ZipRecruiter salary data. Most workers in this role earn between $114,500.00 and $137,500.00 per year, depending on experience, location, and employer.

What is Interpretability in AI?

Interpretability in AI refers to the ability to understand and explain how artificial intelligence systems, especially complex models like neural networks, make their decisions. It helps researchers, developers, and end-users to trust AI systems by making their inner workings more transparent. Interpretability is crucial in sensitive fields such as healthcare and finance, where decisions need to be justified and understood. Techniques for interpretability include feature importance, visualization, and model simplification. Improving interpretability can lead to safer, fairer, and more accountable AI systems.

What is the difference between Interpretability Ai vs Data Scientist?

AspectInterpretability AiData Scientist
Required CredentialsTypically a background in AI, machine learning, or data analysis; often a master's or PhD in related fieldsDegree in computer science, statistics, or related fields; often a master's or PhD
Work EnvironmentResearch labs, AI development teams, tech companies focusing on explainable AIData analysis, modeling, and insights generation across various industries
Employer & Industry UsageTech firms, AI startups, research institutionsFinance, healthcare, tech, consulting, and more

Interpretability Ai specialists focus on making AI models transparent and understandable, often working on explainability tools. Data Scientists analyze data, build models, and generate insights. While both roles require strong analytical skills, Interpretability Ai emphasizes explainability techniques, whereas Data Scientists focus on data analysis and modeling across diverse industries.

What are the key skills and qualifications needed to thrive as an AI Interpretability Specialist, and why are they important?

To thrive as an AI Interpretability Specialist, you need expertise in machine learning, statistics, and data analysis, often backed by a degree in computer science, mathematics, or a related field. Familiarity with interpretability frameworks (like LIME, SHAP), deep learning libraries (such as TensorFlow or PyTorch), and experience with model evaluation tools are typically required. Strong problem-solving abilities, communication skills, and intellectual curiosity help bridge the gap between technical results and stakeholder understanding. These competencies are essential to ensure AI models are transparent, trustworthy, and aligned with ethical standards.

What are the main challenges faced when working in Interpretability AI roles, and how can professionals address them?

Professionals in Interpretability AI often face the challenge of translating complex machine learning models into understandable insights for both technical and non-technical stakeholders. This requires not only a deep understanding of algorithms but also strong communication skills to bridge the gap between data scientists, engineers, and decision-makers. Additionally, balancing the trade-off between model accuracy and interpretability can be tricky, as more interpretable models may sometimes be less accurate. Collaborating closely with cross-functional teams and staying updated with the latest interpretability techniques can help overcome these challenges and add value to AI projects.
More about Interpretability Ai jobs
What cities are hiring for Interpretability Ai jobs? Cities with the most Interpretability Ai job openings:
What states have the most Interpretability Ai jobs? States with the most job openings for Interpretability Ai jobs include:
What job categories do people searching Interpretability Ai jobs look for? The top searched job categories for Interpretability Ai jobs are:

Director, AI Policy

FAS

Washington, DC โ€ข On-site

Full-time

Medical, Dental, Vision, Life, Retirement

Posted 20 days ago

Be an early applicant


Job description

Director, AI PolicyFull-time FAS staffWashington, DCย 

To Sum It Upโ€ฆ

Whatโ€™s the โ€œelevator pitchโ€ for the role?

The Federation of American Scientists is seeking a Director, AI Policy to lead FAS's growing AI portfolio. This person will set strategy, manage staff, oversee major grant-funded projects, work with policymakers, and be responsible for providing sustainably supported pathways to pursue one of the most challenging issues of our time.

The role is designed to sit across several domains of AI policy that are often treated as separate conversations: AI safety and security, fair and trustworthy AI, responsible public-sector use, AI research and development, and uses of AI that can advance public missions such as science, energy, and better government services. The successful candidate will have a clear perspective on the range of risks that AI poses, the opportunities for AI to serve the public interest, and how policy can achieve these goals.ย 

While not expected to have deep subject matter expertise across the entire AI landscape, the ideal candidate will hold strong expertise within at least one domain, with the ability to both proactively demonstrate a willingness to engage with across other domains and manage a team with expertise spanning them. The work requires a spirit of policy entrepreneurship to drive real and lasting policy change.

In short, the ideal candidate will have proven experience in the following areas:ย 

  • Pluralistic AI Approach: Takes potential catastrophic risk seriously without treating topics like fairness, responsible adoption, or public benefit as afterthoughts
  • Visionary Leadership: Ability to see possibilities, set ambitious goals, and inspire others toward a shared mission
  • Relationship Building: Natural connector who builds trust and maintains diverse networks across sectors with an ability to fundraise and drive vision broadlyย 
  • Political Savvy: Understanding of government dynamics, processes, and how to navigate complex political environments
  • Entrepreneurial Mindset: Comfortable with ambiguity, willing to take calculated risks, and focused on results
  • Collaborative Approach: Seeks input, builds consensus, and empowers team members
  • Adaptability: Thrives in a fast-paced environment with shifting priorities and emerging opportunities
  • Integrity: Demonstrates ethical leadership and maintains nonpartisan credibility

What will some of your responsibilities entail?ย ย 

The portfolio

The Director will lead a portfolio that includes, but is not limited to:

  • AI safety and security. Topics could include frontier AI governance, catastrophic and systemic risks, dangerous capability evaluations, model transparency, incident reporting, interpretability, AI-enabled cyber, bio, nuclear, and other national security risks, and government capacity to manage these issues.
  • Fair and trustworthy AI. Topics could include civil rights, discrimination and bias, public-sector use, government procurement, explainability and accountability, privacy, labor, environmental impacts, and community-informed policy development.
  • AI progress in the public interest. Topics could include AI for science, energy innovation, service delivery, government effectiveness, and the design of policy that supports responsible adoption where it can serve the public good.
  • Field building and policy entrepreneurship: fellowships, policy sprints, expert convenings, technical assistance, and programs that help researchers and practitioners turn serious ideas into usable policy.

The FAS AI portfolio is growing. It currently has a multi-million dollar budget for which the Director, AI Policy would be responsible. Current team members include policy experts in frameworks to enhance AI fairness and transparency, and state and local AI governance. We are concurrently seeking to fill two additional mid-level roles, which the Director, AI Policy would also manage, and ideally participate in their final selection. Additional hires would depend on suitable funding levels.

Skills and Expertise: Must-Haves

What skills do you need to demonstrate to be a strong candidate?

Field leader

  • 10+ years of relevant experience across government, think tanks, philanthropy, civil society, academia, industry, or another policy-relevant institution, including substantial work on AI, emerging technology, national security, science and technology policy, civil rights, or related issues.
  • Fluency in AI safety and security policy, including catastrophic and systemic risks from advanced AI systems, including experience engaging with frontier model capabilities, dangerous capability evaluations, misuse risk, incident reporting, interpretability, model transparency, and AI-enabled cyber, bio, nuclear, or other security risks.
  • Expertise in one or more of the following topics: AI safety and security, fair and trustworthy AI, responsible public-sector use, AI research and development, and uses of AI that can advance the public interest.
  • Excellent writing and editing skills, as demonstrated by a strong research or publication record on AI policy, technology governance, national security, civil rights, science and technology policy, or related topics.

Strategic Leadership

  • Experience managing people and complex projects.
  • Develop and execute multi-year strategies to expand the reach, impact, and sustainability of AI portfolio across a number of relevant domains.
  • Serve as a senior member of the FAS leadership team, contributing to organization-wide strategic planning and decision-making.

Portfolio Management

  • Set program vision and strategy and oversee its execution across AI safety and security, fair and trustworthy AI, responsible adoption, AI research and development, and AI for public missions.
  • Oversee portfolio budgets, ensuring efficient resource allocation and financial sustainability.
  • Foster a collaborative, inclusive team culture that values innovation within a policy domain, paired with the ability to integrate work across policy teams to maximize impact.

Fundraising and Partnerships

  • Experience cultivating and stewarding support from philanthropic partners focused on AI safety, global catastrophic risks, science and technology policy, fair and trustworthy AI, and/or AI innovation.ย 
  • Strong relationship management skills, including existing and robust professional networks in relevant domains and the ability to build trust with researchers, advocates, funders, policymakers, civil society organizations, industry experts, and colleagues.

Skills and Expertise: Preferred

  • Experience in government, on Capitol Hill, in a federal agency, or in a state policy role.
  • Experience engaging policymakers, especially Congress, federal agencies, or state governments.
  • Experience briefing senior decision-makers.
  • Experience convening groups that do not usually work together, especially across technical, policy, civil society, industry, and community-based organizations.
  • Hands-on technical experience in AI, machine learning, data science, computer science, or another technical field relevant to AI governance.
  • Advanced degree, such as an MS, JD, MPP/MPA, MBA, or PhD, in a field relevant to AI governance, public policy, computer science, national security, law, social science, or science and technology policy.

Why FAS?ย ย 

Does FAS sound like an organization that you would be energized to join?ย  Is it aligned to your values?

The Federation of American Scientists (FAS) takes seriously its role as a beacon and voice for the science community. Founded in the aftermath of Hiroshima and Nagasaki by scientists concerned about the misuse of science, FAS has a long history of working to ensure that advances in science and technology serve the public good.

Today, FAS is a group of entrepreneurial, mission-driven changemakers working at the intersection of science, technology, and policy. We value fairness, inclusion, transparency, and impact, and we aim to ensure that transformative technologies like AI are governed responsibly and democratically.

Work Environmentย 

This position will be a hybrid role. Meaning that both remote and in-person work can be accommodated, generally two to three days per week on-site, and two to three days per week remote depending on the needs of the organization.

Salary Range

  • $175,000-215,000
BenefitsFAS offers a competitive and comprehensive benefits package that supports employeesโ€™ health, financial security, and overall well-being. Benefits include a competitive 403(b) retirement plan, medical, dental, and vision coverage, short-term and long-term disability insurance, life insurance, employee assistance support, pre-tax benefits such as healthcare and dependent care FSAs, and commuter benefits.

Hiring Statement

Donโ€™t check off every box? Apply anyway! Studies have shown that women and people of color are less likely to apply for jobs unless they meet every listed qualification. At FAS we are dedicated to building a diverse and inclusive workplace, and developing new voices. If youโ€™re excited about this role but your past experience doesnโ€™t align perfectly, we encourage you to apply anyway โ€“ you might just be the right candidate.

The Federation of American Scientists is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender identity or expression, national origin, age, disability, genetic information, marital status, amnesty, or status as a covered veteran in accordance with applicable federal, state and local laws. The Federation of American Scientists prohibits discriminating against employees and job applicants who inquire about, discuss, or disclose the compensation of the employee or applicant or another employee or applicant.ย  Employment is contingent on successful verification of eligibility to work in the United States.ย 


Powered by JazzHR

tWPVcV6GOS