Research Engineer (AI Pentest)

TL;DR

Research Engineer (AI Pentest): Building feedback loops and agentic architectures to improve AI-driven vulnerability discovery with an accent on data-driven experimentation and system reliability. Focus on designing automated feedback loops, building benchmarks, and shipping production-quality improvements to the AI pentesting platform.

Location: Ghent, Belgium

Company

hirify.global is a developer-first security startup building self-securing software products to reduce risk without slowing down development teams.

What you will do

• Improve agent performance in finding, verifying, and reporting vulnerabilities.
• Design automated feedback loops to convert agent traces and failures into system improvements.
• Run data-driven experiments with agentic architectures, workflows, and prompts.
• Build evals, benchmarks, and regression tests to measure progress.
• Optimize the platform for reliability, accuracy, and cost-efficiency.
• Ship validated improvements to production and own them end-to-end.

Requirements

• Strong Python skills.
• Hands-on experience building with LLMs, AI workflows, agents, or evals.
• Strong engineering fundamentals and ability to ship production-quality systems.
• Ability to reason from traces, logs, metrics, and failure cases.
• Data-driven mindset with experience designing experiments and measuring impact.
• Security affinity (hacking, pentesting, or application security experience is a plus).

Culture & Benefits

• High-impact position in a fast-growing, well-funded startup.
• Fast growth of responsibility and ownership.
• Competitive salary package.
• Open and informal team atmosphere.
• Flexibility in working hours.