Multi-Agent Triage for Static-Analysis Rules — Amazon

Role: Applied Scientist Intern, Amazon, New York (May – Aug 2026)

  • Reduced validation time for new static-analysis rules from 10–15 days to 2–3 days by automating triage of production findings at 90% accuracy, averaging 4 minutes and $0.50 per finding.
  • Built a three-stage workflow with the Strands Agents SDK to summarize findings, gather code context, and verify results; scored 14 points higher than Claude Code using the same model.
  • Supported all 47 rules from two internal analyzers across Python, Java, and JavaScript without per-rule or per-language tuning.
  • Curated a benchmark of 600+ findings from one year of production triage records, covering every rule; achieved 95% verdict consistency across five runs.
Hulin Wang
Hulin Wang
Ph.D. Candidate · LLM Agents for Vulnerability Discovery & Repair

Ph.D. candidate at ASU SEFCOM building LLM agents that find and fix real-world software vulnerabilities.