Senior Vulnerability Researcher — AI Safety

SD Solutions; United States; Remote; USD 83,000 - 207,000; Full time

Job summary

SD Solutions specializes in building evaluation infrastructure for AI safety and robustness testing. They seek contributors with deep vulnerability research and reverse engineering skills to review AI prompts and assess security implications.

Ideal candidates have 5+ years in vulnerability research, proficiency with IDA/Ghidra/Binary Ninja, and experience fuzzing and patch diffing across x86/x64 and ARM.

Qualifications

• Minimum 5 years of hands-on experience in vulnerability research and reverse engineering.
• Proven ability to discover vulnerabilities through fuzzing, static and dynamic analysis, and patch diffing.
• Fluent use of IDA, Ghidra, Binary Ninja, and debuggers on x86/x64 and ARM binaries.

Responsibilities

• Review cybersecurity prompts submitted to an AI system to judge benign vs. malicious.
• Determine the underlying intent and goal of each prompt and assess legitimacy or harm.
• Apply deep domain expertise to judge technical context, specificity, and real-world uplift a response would give an attacker.

Skills

Vulnerability research

Reverse engineering

Fuzzing

Static analysis

Dynamic analysis

Debugging

Patch diffing

Tools

IDA

Ghidra

Binary Ninja

GDB

Job description

SD Solutions specializes in building evaluation infrastructure for AI safety and robustness testing. They seek contributors with deep vulnerability research and reverse engineering skills to review AI prompts and assess security implications.

Ideal candidates have 5+ years in vulnerability research, proficiency with IDA/Ghidra/Binary Ninja, and experience fuzzing and patch diffing across x86/x64 and ARM.