About this role
Build and harden Nullify's multi-provider agent runtime to detect, validate, and prepare fixes for vulnerabilities, design agents that reason about application behavior, and develop evaluation harnesses with labelled test cases, scoring, and regression tracking. Own agents end-to-end including detection, validation, fix generation, and judgment calls between steps.
Skills for this role
GoPythonLarge Language Models (LLMs)LLM-based agentsAgent runtimesDistributed systemsCheckpointingMulti-step reasoningTool use (LLM agents)Evaluation harnessesLabelled test casesScoringRegression trackingProduction systemsApplication security