Software Engineer, Cybersecurity Benchmarks

Epoch AI

. Build and maintain cybersecurity benchmarks for AI within evaluation infrastructure, primarily using the Inspect library .

Posted 11/10/2026full-timeRemote • United StatesMid-LevelSenior💰 $150,000 - $350,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and maintaining cybersecurity benchmarks for AI, with a strong foundation in software engineering and experience in sandboxing and red teaming against advanced adversaries. Proficient in collaborating with cross-functional teams to ensure accurate evaluation data and strategic input on AI cybersecurity evaluation.

Highest-signal resume keywords

Software Engineering ExperienceSandboxing SoftwareRed Team ExperienceBenchmarking AIsProfessional Level English Proficiency

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Building Complex SystemsMaintaining Robust CodeThreat ModellingEvaluating AI ModelsGenerating Benchmark Ideas

Soft Skills

CollaborationStrategic InputMotivation from Mission

Tools & Technologies

Inspect LibraryCTF InfrastructureAI Coding Harnesses

Industry Keywords

CybersecurityAI TrendsEthical HackingAgentic AI

Tech Stack

Tools & technologies

Cyber Security

About the role

Key responsibilities & impact

Build and maintain cybersecurity benchmarks for AI within evaluation infrastructure, primarily using the Inspect library
Pitch and prototype ideas for new benchmarks and experiments
Keep the benchmark suite running so new model releases can be evaluated quickly
Sandbox and harden evaluation environments against highly capable AI models
Monitor how AI agents and coding harnesses interact with environments
Use threat modelling to inform benchmarking approaches and measurement decisions
Provide strategic input on AI cybersecurity evaluation strategy
Integrate with AI providers and configure benchmarks to run on infrastructure
Collaborate with researchers, analysts, and engineers to ensure evaluation data and outputs are accurate, insightful, and integrated into research products and publications
Report to the CTO

Requirements

What you’ll need

Strong software engineering experience, including several years building and maintaining complex systems and regularly contributing robust, maintainable code
Experience sandboxing software against highly capable adversaries
Red team experience ethically hacking software
Familiarity with agentic AI use and coding harnesses
Ability to generate ideas for new benchmarks and experiments
Motivation from Epoch AI’s mission to provide rigorous, independent insight into key trends in AI
Professional level English proficiency
Applications must be submitted in English
Experience benchmarking AIs and running evaluations (nice-to-have)
Experience setting up CTF infrastructure (nice-to-have)
Experience using modern AI for red teaming or ethically hacking (nice-to-have)
Knowledge of the inner workings of AI coding harnesses and tool calls (nice-to-have)
Familiarity with inspect_ai (nice-to-have)
Solid grasp of current AI trends (nice-to-have)

Benefits

Comp & perks

Fully remote work
Full-time, flexible work hours
No required travel
Preference for candidates able to travel to three retreats per year
Inclusive, equitable, and supportive community
Accessibility support and application deadline extension requests