Related skills
bigquery sql python go typescript📋 Description
- Design LLM guardrails to detect abuse in AI-generated code and agent interactions
- Build AI detectors using LLMs to identify threats and automate responses
- Operate abuse detection across millions of daily user actions
- Design automated responses that enforce policies without manual intervention
- Own end-to-end abuse lifecycle: detection, investigation, enforcement, appeals
- Analyze attack patterns with BigQuery and Hex to derive new detections
🎯 Requirements
- 4+ years in security engineering, anti-abuse, trust & safety, or fraud detection
- Strong Python and/or TypeScript skills for detection systems
- SQL and data analysis at scale (BigQuery, Snowflake, or similar)
- Experience with ML/LLM classifiers for security/abuse detection
- Familiarity with prompt injection, jailbreaking, and LLM attack vectors
- Investigate complex abuse patterns and translate findings into automated defenses
🎁 Benefits
- Competitive Salary & Equity
- 401(k) with 4% match (US)
- Health, Dental, Vision and Life Insurance
- Short Term and Long Term Disability
- Paid parental, medical, caregiver leave
- Flexible Time Off (FTO) + Holidays
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!