Software Engineer, Cybersecurity Benchmarks

11 hours, 16 minutes ago
Full-time
Senior
Software Development
Epoch AI

Epoch AI

Epoch is a research institute focused on exploring critical trends and questions that influence the development and governance of artificial intelligence, providing valuable insights into its societal implications.

Professional Services
1-10
Founded 2022

Description

  • Design, build, and maintain AI cybersecurity benchmarks, primarily using the Inspect library.
  • Propose and prototype new cybersecurity benchmarks and evaluation experiments.
  • Maintain the benchmark suite to enable rapid evaluation of new AI model releases.
  • Sandbox and harden evaluation environments to prevent capable AI models from escaping.
  • Use threat modeling to determine evaluation priorities and shape cybersecurity benchmarking strategy.
  • Monitor how AI agents and coding harnesses interact with evaluation environments.
  • Integrate AI providers and configure benchmarks to run on Epoch AI infrastructure.
  • Collaborate with researchers, analysts, and engineers to ensure evaluation outputs are accurate and incorporated into research publications.

Requirements

  • Several years of software engineering experience building and maintaining complex systems with robust, maintainable code.
  • Experience sandboxing software against highly capable adversaries.
  • Red-team experience ethically hacking software.
  • Familiarity with agentic AI use and AI coding harnesses.
  • Ability to generate ideas for new benchmarks and experiments.
  • Motivation to support rigorous, independent public evaluation of AI capabilities.
  • Professional-level English proficiency.
  • Ability to work full-time with preferred overlap between UTC–8 and UTC.
  • Experience benchmarking AI systems and running evaluations (preferred).
  • Experience with CTF infrastructure, AI-enabled red teaming, inspect_ai, AI coding harness tool calls, or current AI trends (preferred).

Benefits

  • Compensation of $150,000 to $350,000.
  • Fully remote role with hiring available in many countries.
  • Flexible full-time work hours.
  • No required travel.
  • Opportunity to attend three company retreats per year.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Process Automation Engineer, Provisioning & Onboarding

SentinelOne 1001-5000 Internet Software & Services

SentinelOne is seeking a Process Automation Engineer, Provisioning & Onboarding to automate customer access and entitlement workflows, improving operational reliability and supporting product growth across its AI-native cybersecurity platform.

Cybersecurity Python Salesforce
9 hours, 1 minute ago

Junior Software Engineer

CSC Generation 501-1000 Internet Software & Services

One Kings Lane, part of CSC Generation, is seeking a remote Junior Software Engineer to build and improve shared full-stack tooling for consumer e-commerce storefronts across its brand portfolio.

CSS Design Systems E-commerce Express.js Git HTML HTTP JavaScript JSON Next.js Node.js React REST API TypeScript UX Design
9 hours, 1 minute ago

Senior Software Engineer, AI-Driven Systems

Thimble 51-200 Insurance

Thimble is seeking a Backend Engineer to modernize its AWS-based insurance platform by building durable, AI-assisted workflows and services for broker and distribution-partner growth.

Angular AWS Microservices Node.js React TypeScript
11 hours, 1 minute ago

NetSuite Developer

Cologix 201-500 Diversified Telecommunication Services

Cologix is hiring a NetSuite Developer to build, enhance, and support customizations and integrations that power its internal corporate systems across a North American data center platform.

Agile Cybersecurity Git JavaScript NetSuite REST API Scrum
11 hours, 16 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers