OverviewWe’re building a new security research team and looking for an engineer who combines practical security research with strong software development and automation skills.
You’ll contribute to triage, vulnerability analysis, PoC development, and reporting while building the LLM harnesses and research infrastructure that support the team’s work. Hands-on experience building or substantially extending an LLM or agent harness is required.
Pay Range $118,000 - $203,000
The pay range for this position is a general guideline only and not a guarantee of compensation or salary. Additional factors considered in extending an offer include (but are not limited to) responsibilities of job, education, experience, knowledge, skills, and abilities, as well as internal equity, alignment with market data, geographic location, and any applicable laws.
Responsibilities
In this role, you will:
- Triage findings, reproduce vulnerabilities, and support root-cause analysis and PoC development.
- Build and maintain LLM harnesses that connect models with research tools, relevant context, and execution environments.
- Develop automation for code and binary analysis, experimentation, evidence collection, and report generation.
- Improve workflow reliability through logging, execution controls, reproducibility, and evaluations.
- Verify generated code and findings against observable system behavior.
- Maintain reusable scripts, research environments, and documentation.
- Work with researchers to turn useful investigation techniques into dependable tools.
Qualifications
You should bring:
- At least 3 years in security research, software engineering, security tooling, or closely related work.
- Bachelor’s degree in Computer Engineering, Computer Science, or a related technical field. Additional years of experience may substitute for degree.
- Demonstrated vulnerability analysis experience, including reproducing issues and understanding their root causes.
- Strong programming skills and experience building tools that other people can use and maintain.
- Practical experience building or substantially extending LLM harnesses, including tool integration and troubleshooting.
- Familiarity with reverse engineering, debugging, and PoC development.
- Clear technical writing and the ability to document evidence, assumptions, and limitations.
Preferred:
- Experience with sandboxed execution, fuzzing infrastructure, automated evaluations, or reproducible research environments would be valuable.
Security Clearance:
- Active Top Secret/SCI clearance.
- U.S. Citizenship is required.
