Researcher, Conceptual Reasoning Capabilities

Aisafety

Berkeley (CA)

On-site

USD 90,000 - 150,000

Full time

13 days ago

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Redwood Research is seeking a researcher to join the Conceptual Reasoning Capabilities team focused on evaluating and improving AI through reasoning about questions in philosophy, AI strategy, and safety that lack verifiable answers.

The role involves creating datasets, building model scaffolds, running training experiments, and contributing ideas while communicating research impact. Collaboration with labs and stakeholders may be part of the work.

Qualifications

  • Clear thinking in conceptual domains: unusual sharpness at written argumentation.

Responsibilities

  • Create datasets for research on conceptual reasoning.
  • Build scaffolds for models and run training experiments.
  • Generate new project ideas and communicate research impact.
  • Manage other researchers or coordinate with AI labs and stakeholders.

Job description

About Redwood Research

At Redwood Research, we strive to ensure the safe development of artificial intelligence through rigorous technical research, thoughtful analysis, and strategic advising.

About the role

The Conceptual Reasoning Capabilities (CRC) team works on evaluating and improving AI at conceptual reasoning: reasoning about the kinds of questions commonly found in philosophy, AI strategy, and AI safety that don't have a (practically) verifiable answer and where progress comes from argumentation. We think answering these questions well is the skill AIs most urgently need to help with mitigating AI risk.

The bulk of our work is creating datasets. Depending on your skills and experience, you might also build scaffolds for models, run training experiments, come up with new project ideas, communicate our research and theory of impact, manage other researchers, or help manage our relationships with AI labs and other stakeholders.

Explore our past work at conceptualreasoning.ai.

Requirements
  • Clear thinking in conceptual domains: We are looking for people who are unusually sharp at written argumentation. A strong candidate can easily assess the logical validity of an argument and weigh the strength of fuzzy, hard-to-formalize arguments.

  • Grit: Our projects require the willingness to spend a lot of time grinding through tasks such as carefully evaluating dozens of LLM-written arguments or manually writing rubrics with hundreds of items.

  • A deep interest in either AI risk or acausal interactions

Preferred skills
  • Conceptual creativity: The ability to develop novel ideas and arguments

  • Experience in a conceptual domain

  • Experience interacting with LLMs: using coding agents, building scaffolds, or engineering prompts

  • Strong communication and collaboration skills

  • Experience training LLMs

  • Management experience

How we hire

Our application process includes work tests and interviews. In most cases we will not offer a full-time position immediately, but instead offer a 4-month work trial.

We are committed to diversity and equal opportunity in all aspects of our hiring process. We do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. We welcome and encourage all qualified candidates to apply for our open positions.

We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Conceptual Reasoning Capabilities Team Researcher
Conceptual Reasoning Capabilities Team Researcher

Redwood Research • Berkeley (CA)

On-site
USD 90,000 - 150,000
Conceptual Reasoning Researcher for AI Safety & Theory
Conceptual Reasoning Researcher for AI Safety & Theory

Redwood Research • Berkeley (CA)

On-site
USD 90,000 - 150,000
Empirical Researcher
Empirical Researcher

Redwood Research • Berkeley (CA)

On-site
USD 120,000 - 180,000
Remote AI Safety Conceptual Reasoning Researcher
Remote AI Safety Conceptual Reasoning Researcher

Trajectory Labs, PBC • United States

Hybrid
USD 138,000 - 207,000
Conceptual Reasoning Researcher (Contract)
Conceptual Reasoning Researcher (Contract)

Trajectory Labs, PBC • United States

Hybrid
USD 138,000 - 207,000
Conceptual Reasoning & AI Safety Researcher
Conceptual Reasoning & AI Safety Researcher

Effectief Altruisme • United States

Remote
USD 70,000 - 110,000
Artificial Intelligence Researcher
Artificial Intelligence Researcher

Cerebro • San Francisco (CA)

On-site
USD 160,000 - 230,000
Member of Technical Staff [Research]
Member of Technical Staff [Research]

NeoCognition • Palo Alto (CA)

On-site
USD 120,000 - 150,000
Lead Research Scientist, LLM Agents & Systems
Lead Research Scientist, LLM Agents & Systems

NeoCognition • Palo Alto (CA)

On-site
USD 120,000 - 150,000
Research Engineer/Scientist
Research Engineer/Scientist

AI Safety, Inc • San Francisco (CA)

On-site
USD 140,000 - 200,000
Health insurance
401K plan + 4% matching
Unlimited PTO
+2