Staff Software Engineer, Risk

Builds AI-powered detection and response systems to defend Replit from abuse.

• •Replit's Risk team builds detection and automated response systems to defend the AI-native platform from abuse, including phishing, cryptomining, fraud, and LLM-specific attacks.
• •Key Responsibilities Design and implement LLM guardrails and AI-powered detection systems Build and operate abuse detection for phishing, cryptomining, account takeover, and fraud Design automated enforcement and own the abuse response lifecycle Analyze attack patterns using BigQuery and Hex and extend internal monitoring tools Requirements 8+ years in security engineering, anti-abuse, trust & safety, or fraud detection Strong programming skills in Python and/or TypeScript Experience with SQL and large-scale data analysis (BigQuery, Snowflake, etc.) Experience building or fine-tuning ML/LLM classifiers and familiarity with prompt injection attacks Clear communication across Security, Support, Legal, and Engineering