Researcher, Benchmark Reviews

Epoch Ai

Remote, Remote

RemoteCareer-pivot friendly

Who this role is best for

Mid-level researchers comfortable with remote work and coding agents will find this role aligned with public-facing AI benchmark analysis.

Best fit for

Analytical thinkers adept at evaluating AI methodologies without full delegation to tools.
— “evaluate their methodologies, and write up your findings”
Remote professionals capable of producing a steady stream of technical critiques.
— “produce a steady stream of benchmark reviews”
Researchers comfortable using coding agents while maintaining independent judgment.
— “comfortable using coding agents to help you, without delegating your judgment”

Things to consider

Public-facing writing is a core deliverable, not an occasional task.
— “write up your findings in public-facing research”
Applications are accepted on a rolling basis without fixed deadlines.
— “Applications are rolling”

How to stand out

Showcase prior benchmark analysis work or similar technical critiques.
— “Examples of the kind of reports you would produce”
Demonstrate experience with coding agents in a research context.
— “comfortable using coding agents to help you”
Omit personal details and focus strictly on professional qualifications.
— “do not include a cover letter, photograph, or headshot”

Pace · SteadyCollaboration · LowAutonomy · HighDecision Impact · IndividualLevel · Junior

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

publishing benchmark reviews
analyzing AI benchmarks

Typical background

research experienceAI benchmarking

Skills & requirements

Required

AI Benchmark AnalysisMethodology EvaluationPublic Research Writing

Preferred

Coding Agents

About the role

Original posting from Epoch Ai via Lever

Epoch AI is looking for a Researcher to develop and publish critiques and reviews of AI benchmarks.
About the role
We are looking for a Researcher to produce a steady stream of benchmark reviews. You will closely analyze a wide variety of new benchmarks, evaluate their methodologies, and write up your findings in public-facing research. You should be comfortable using coding agents to help you, without delegating your judgment.
Examples of the kind of reports you would produce include our reviews of SWE-bench Verified, OSWorld, and economic value benchmarks.
This role is fully remote; we are able to hire in many countries. We invite anyone who is interested to apply, regardless of background, experience, or credentials. Please do not include a cover letter, photograph, or headshot of yourself, or any personal information that is not relevant to the role for which you're applying (including marital status, age, identity traits, etc.).
If this role sounds interesting, we are also looking for researchers on multiple other teams.
Applications are rolling.

Source: Epoch Ai careers (Lever)