1

Mechanistic Interpretability Jobs (NOW HIRING)

Research Engineer, AI

New York, NY · Hybrid

$214K - $375K/yr

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

... mechanistic understanding and controllability. I'm looking for Research Engineers who want to build the experimental infrastructure that makes cutting-edge interpretability research possible. What ...

Research Scientist, AI

Redwood City, CA · Hybrid

$214K - $375K/yr

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

Research Scientist, AI

New York, NY · Hybrid

$214K - $375K/yr

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

Research Engineer, AI

Redwood City, CA · Hybrid

$214K - $375K/yr

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

Research Engineer, AI

Redwood City, CA · On-site +1

$214K - $375K/yr

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

Research Engineer, AI

New York, NY · On-site +1

$214K - $375K/yr

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

Research Scientist, AI

New York, NY · On-site +1

$214K - $375K/yr

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

Research Scientist, AI

Redwood City, CA · On-site +1

$214K - $375K/yr

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

$150K - $250K/yr

Mechanistic Interpretability : Finding issues with Sparse Autoencoders, probing deception using AmongUs, understanding learned planning in SokoBan and interpretable data attribution. FAR.AI is one of ...

Machine Learning Engineer, AI

New York, NY · On-site +1

$214K - $335K/yr

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

Mechanistic interpretability of biological foundation models: extracting new biological knowledge directly from model weights * Scientific data at unprecedented scale: AI systems to collect, curate ...

$120K - $190K/yr

Mechanistic Interpretability : Finding issues with Sparse Autoencoders, probing deception using AmongUs, understanding learned planning in SokoBan and interpretable data attribution. FAR.AI is one of ...

$100K - $190K/yr

Mechanistic Interpretability : Finding issues with Sparse Autoencoders, probing deception using AmongUs, understanding learned planning in SokoBan and interpretable data attribution. FAR.AI is one of ...

next page

Showing results 1-20

Mechanistic Interpretability information

See salary details

$31K

$36.3K

$50.5K

How much do mechanistic interpretability jobs pay per year?

As of Jul 7, 2026, the average yearly pay for mechanistic interpretability in the United States is $36,260.00, according to ZipRecruiter salary data. Most workers in this role earn between $33,500.00 and $34,000.00 per year, depending on experience, location, and employer.

How to become mech interp researcher?

To become a mechanistic interpretability researcher, typically a strong background in machine learning, deep learning, and programming (e.g., Python) is required. Gaining expertise through advanced degrees such as a master's or Ph.D. in computer science, neuroscience, or related fields, along with experience in analyzing neural networks and using interpretability tools, is essential for this role.

What is the difference between Mechanistic Interpretability vs Data Scientist?

AspectMechanistic InterpretabilityData Scientist
Required credentialsAdvanced degrees in AI, ML, or related fieldsDegree in Data Science, Statistics, or Computer Science
Work environmentResearch labs, AI development teamsBusiness, tech companies, consulting firms
Industry usageAI research, model transparency, safetyData analysis, predictive modeling, insights
Search intentUnderstanding model internals, interpretability techniquesData analysis, insights, model building

Mechanistic Interpretability focuses on understanding how AI models work internally, often requiring deep technical expertise. Data Scientists analyze data to build models and extract insights. While both roles involve data and algorithms, Mechanistic Interpretability is more research-oriented, emphasizing transparency and safety of AI systems, whereas Data Scientists focus on practical data analysis and modeling for business applications.

Is ML a high paying job?

Mechanistic interpretability is a specialized area within machine learning that often requires advanced skills in deep learning, programming, and mathematics. Salaries for machine learning roles vary widely depending on experience, location, and industry, but generally, ML jobs tend to be well-compensated compared to many other tech roles, especially at senior levels or in research positions. Entry-level positions may offer lower salaries, but experienced professionals in this field can earn high six-figure incomes or more.

Which 5 jobs will survive AI?

Mechanistic interpretability is a specialized field within AI research focused on understanding how models work. Jobs in AI safety, research, and development that require deep technical expertise and critical thinking are likely to persist, as they involve tasks that are difficult to automate. Roles emphasizing creativity, complex problem-solving, and human judgment, such as AI ethicists or interdisciplinary researchers, are also expected to remain relevant.

How does mechanistic interpretability work?

Mechanistic interpretability involves analyzing neural networks by examining their internal components, such as neurons and weights, to understand how they process information. It often requires techniques like feature visualization, circuit analysis, and the use of specialized tools to trace decision pathways, helping researchers identify how specific features influence model outputs.
More about Mechanistic Interpretability jobs
What cities are hiring for Mechanistic Interpretability jobs? Cities with the most Mechanistic Interpretability job openings:
What states have the most Mechanistic Interpretability jobs? States with the most job openings for Mechanistic Interpretability jobs include:
What job categories do people searching Mechanistic Interpretability jobs look for? The top searched job categories for Mechanistic Interpretability jobs are:
Infographic showing various Mechanistic Interpretability job openings in the United States as of July 2026, with employment types broken down into 100% Full Time. Highlights an 87% Physical, 3% Hybrid, and 10% Remote job distribution, with an average salary of $36,260 per year, or $17.4 per hour.

Senior Program Scientist, AI and Advanced Computing Institute

Schmidt Sciences

Manhattan, NY • On-site

$100K - $137K/yr

Full-time

Posted 3 days ago


Job description

Job Summary:
Schmidt Sciences is a nonprofit organization focused on accelerating scientific knowledge and breakthroughs using advanced tools. The Senior Program Scientist will provide technical leadership and manage programs within the AI Institute, aiming to position it as a leading funder of AI scientific research globally.
Responsibilities:
• Support the Institute lead in the design, evolution, and execution of the AI Institute’s current and future strategic, scientific, and technical direction.
• Co-design multi-year research agendas.
• Identify areas of AI where early philanthropy entry can provide significant advancement.
• Contribute to the overall scientific priorities in the AI and advanced computing portfolio and set future directions for engagement.
• Provide technical advice to the existing programs and major awards of the AI Institute.
• As needed, work with team members to develop new programs. Note: current program explorations include AI interpretability, evolution of communication of multi-agent systems, post-transistor AI hardware, and AI-enabled simulation of scientific processes.
• Support existing AI Institute programs by providing networking assistance, scientific expertise, and mentorship, as necessary, and by working closely and collaboratively with the teams responsible for delivery. Contribute to the team’s assessment of expressions of interest and research proposals.
• Manage 3-5 program scientists and visiting scientists to help them continue to grow their scientific discernment and grantmaking skills.
• Contribute to the improvement of the AI team’s operations, including our grantmaking, budgeting, events & convening, and other processes.
• Act as a conduit for bringing in innovative ideas and perspectives from the AI community, actively engaging with stakeholders to identify emerging trends and opportunities for collaboration.
• Serve as an expert advisor at Schmidt Sciences on topics in AI and advanced computing, with a focus on AI and humanities.
• Work with other members of the Schmidt Sciences team to drive organizational priorities and model our values.
• Identify potential partners for Schmidt Sciences, including universities, labs, other research facilities, and philanthropic and government organizations.
• Participate in relevant industry or academic conferences and events, representing Schmidt Sciences’ presence on AI and advanced computing issues.
Qualifications:
Required:
• Advanced degree (e.g., PhD), from an accredited institution, with a focus on artificial intelligence
• 10+ years of academic and industry experience in artificial intelligence
• Deep understanding of modern machine learning, including deep learning, probabilistic modeling, generative models, reinforcement learning, and large-scale representation learning
• Experience leading teams and managing technical staff
• Hands-on experience designing, training, and evaluating state-of-the-art models (e.g., foundation models, multimodal systems, agentic AI, simulation-based models)
• Demonstrated track record of scientific accomplishments, evidenced by peer-reviewed publications, patents, successful grant applications, or contributions to innovative industry projects
• Ability to critically evaluate scientific, technical, and other AI-related claims in grant proposals and other technical opportunities and emerging methods
• Deep relationships in the AI community and experience working with AI-focused institutions
• Experience producing technical writing for expert and general audiences
• Demonstrated ability to collaborate and a record of impact in high-intensity, team-based environments
• Sense of urgency in driving work to completion
• The highest integrity and ability to maintain confidentiality
• Be able to travel within the U.S. and internationally on a regular basis as needed
Preferred:
• Hands-on AI Experience: Experience building prototypes, benchmarks, or proof-of-concept systems to test scientific hypotheses or assess research investments. Strong fluency in ML engineering tools and best practices (Python, PyTorch/JAX/TF, data pipelines, MLOps, evaluation frameworks). Experience evaluating the scalability, data requirements, compute needs, and infrastructure implications of ambitious AI projects.
• Expertise in Specific Focus Areas for the AI Institute, Including: AI model evaluation and red-teaming for scientific reliability, Mechanistic interpretability or auditing methods, Multi-agent systems and emergent behavior, AI-accelerated simulation frameworks
• AI x Science: Familiarity with how AI is used across scientific disciplines (biology, chemistry, physics, climate science, neuroscience, etc.). Expertise in at least one scientific domain where AI is meaningfully accelerating research (e.g., protein structure prediction, generative chemistry, computational biology, materials discovery, climate modeling). Ability to work and translate technical concepts across multiple scientific disciplines
• Strategy and Partnerships: Experience designing grantmaking / funding programs in philanthropy or government. Experience working with other science-focused institutions, such as philanthropic organizations or academic research institutions. Ability to identify underfunded opportunities and “white space” where philanthropy can uniquely accelerate scientific progress. Public profile and extensive network in the sciences that will allow Schmidt Sciences to continue to build on our reputation in this area
Company:
Schmidt Sciences is a philanthropy dedicated to fostering the advancement of science and technology. Founded in 2024, the company is headquartered in , , with a team of 11-50 employees. The company is currently Early Stage.