AI Pentest Research Engineer - Build Smarter Security Tests

aikidosecurity; Oost-Vlaanderen; Sur place; EUR 70 000 - 110 000; Plein temps

Avantages offerts par ce poste

Competitive salary package

Flexible working hours

Open, informal culture

Résumé du poste

Aikido Security is hiring a Research Engineer for its AI Pentest team. You will build feedback loops, improve agent performance, and turn traces and data into measurable gains in vulnerability discovery, verification, and reporting.

You’ll work with Python-based tooling, LLMs, and AI workflows to design experiments, run benchmarks, and ship production‑ready improvements end‑to‑end in a fast‑growing security company.

Qualifications

• Strong Python skills.
• Hands-on experience building with LLMs, AI workflows, agents, evals, or other AI-native systems.
• Strong engineering fundamentals and the ability to ship production-quality systems independently.
• Ability to reason from traces, logs, metrics, and failure cases to improve system behavior.
• Data-driven mindset: comfortable designing experiments, measuring impact, and making trade-offs between quality, speed, cost, and reliability.
• Security affinity, with hacking, pentesting, bug bounty, or application security experience as a strong plus.
• Self-starter who thrives in ambiguous environments without a rigid structure.

Responsabilités

• Make our agents measurably better at finding, verifying, and reporting vulnerabilities.
• Design automated feedback loops that convert agent traces and failures into improvements of the agent harness.
• Run data-driven experiments with different agentic architectures, workflows, tools, prompts, and eval strategies.
• Build evals, benchmarks, and regression tests to measure progress and prevent regressions.
• Improve the reliability, performance, accuracy, and cost-efficiency of our AI pentesting platform.
• Ship validated improvements to production and own them end-to-end.

Connaissances

Python

LLMs

Engineering fundamentals

Trace/logs analysis

Data-driven mindset

Security experience

Autonomy

Description du poste

Aikido Security is hiring a Research Engineer for its AI Pentest team. You will build feedback loops, improve agent performance, and turn traces and data into measurable gains in vulnerability discovery, verification, and reporting.

You’ll work with Python-based tooling, LLMs, and AI workflows to design experiments, run benchmarks, and ship production‑ready improvements end‑to‑end in a fast‑growing security company.