14 days ago
Foster City, CA, USAStaff+
Base Salary
$190k - $240k/yr
Responsibilities
- Design and implement LLM guardrails for detecting abuse in AI-generated code.
- Build AI-powered detection systems to identify malicious patterns and automate responses.
- Operate abuse detection systems for phishing, cryptomining, and financial fraud.
- Design automated response mechanisms to enforce platform policies.
- Manage the full abuse response lifecycle, including detection and enforcement.
- Analyze attack patterns and develop new detection rules.
- Maintain and extend internal detection tools for user activity monitoring.
- Integrate security scanners into CI pipelines with performance SLAs.
- Track abuse trends and adapt defenses as attack patterns evolve.
Requirements
- 8+ years of experience in security engineering or anti-abuse.
- Strong programming skills in Python and/or TypeScript.
- Experience with SQL and data analysis at scale.
- Experience building or fine-tuning ML/LLM-based classifiers.
- Familiarity with prompt injection and LLM-specific attack vectors.
- Ability to investigate complex abuse patterns and automate defenses.
- Familiarity with common attack patterns like phishing and account takeover.
- Clear communication skills for cross-team collaboration.
Benefits
- Competitive Salary & Equity.
- 401(k) Program with a 4% match.
- Health, Dental, Vision, and Life Insurance.
- Short Term and Long Term Disability.
- Paid Parental, Medical, and Caregiver Leave.
- Commuter Benefits.
- Monthly Wellness Stipend.
- Autonomous Work Environment.
- In Office Set-Up Reimbursement.
- Flexible Time Off (FTO) + Holidays.
- Quarterly Team Gatherings.
- In Office Amenities.