FREE ACCESS
5,000–10,000 jobs/day
See all jobs on Scoutfield
Search thousands of fresh jobs every day.
Discover
- Fresh listings
- Fast filters
- No subscription required
Create a free account and start exploring right away.
Research Intern – AI Security
exponential.fi. Build security environments, adversarial agents, and evaluations for frontier AI systems .
Core Competencies
Role fitCore Competencies
Use this summary to align your resume positioning with the role.
Demonstrates expertise in building and evaluating machine learning systems, with a focus on AI security and adversarial machine learning. Capable of conducting controlled experiments and analyzing model behavior to contribute valuable research findings.
Highest-signal resume keywords
Machine LearningAI SecurityAdversarial Machine LearningReinforcement LearningProgramming Skills
ATS Keywords
Tailor your resumeApplicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard Skills
Machine LearningAI SecurityAdversarial Machine LearningReinforcement LearningProgramming SkillsResearch CodebasesControlled ExperimentsModel Behavior AnalysisOpen-Source ContributionsTechnical Publication
Soft Skills
CuriosityDisciplineIndependenceFeedback Seeking
Industry Keywords
AI AgentsAgentic SystemsRed TeamingAI Safety EvaluationsReproducible Experiments
About the role
Key responsibilities & impact- Build security environments, adversarial agents, and evaluations for frontier AI systems
- Work across AI security, machine learning, and research engineering alongside the core team
- Take ownership of a technically ambitious project in agent security
- Design and implement the approach
- Run controlled experiments with clear baselines and verifiable outcomes
- Analyze model behavior and communicate results to the team
- Contribute code, evaluations, and research findings that remain useful after the internship
Requirements
What you’ll need- Current study or recent work in machine learning, computer science, security, or a related field
- Strong programming skills
- Experience building or evaluating machine-learning systems
- Curiosity about AI agents
- Discipline to investigate failures carefully
- Ability to work independently and ask for feedback early
- Useful experience with LLMs, reinforcement learning, or agentic systems
- Useful experience with adversarial machine learning, red teaming, or AI safety evaluations
- Useful experience with research codebases, reproducible experiments, or open-source contributions
- A previous research project, thesis, or technical publication is useful
Benefits
Comp & perks- Competitive compensation
- Flexible hours
- Remote-friendly setup
- Vacation budget
- Learning budget
- Conference budget
- Research freedom in a high-trust environment