Research Engineer, AI Security
Core
Improve the judgment, reasoning, and reliability of AI security agents that continuously attack and validate production systems.
Role type
Senior Research Engineer (AI Security)
Builds
AI security agents, evaluation frameworks, and production-grade security tools
Domain
AI Security / LLM Agents / Cybersecurity
Deliverable
production ML models
Required skills
LLM-based agent development, empirical evaluation design, Python/TypeScript/Go, LLM security (prompt injection, jailbreaks), system reasoning
Preferred skills
ML research background, offensive security (red teaming, bug bounty), reinforcement learning, graph data models
Technologies
Python, TypeScript, Go, LLMs, graph databases
Responsibilities
Design experiments and benchmarks to evaluate agent performance; tune models and prompts for cost/latency/quality; harden agents against prompt injection and data exfiltration; build tools for verification and self-checks at scale; analyze customer engagement data to fix reasoning failures
Seniority
Senior, hands-on IC
