Senior Software Engineer (Agentic Systems)

Join our team as a Senior Software Engineer specializing in Agentic Systems. You will be responsible for building and evolving an autonomous web application penetration tester that mimics the skills of a skilled human pentester. Your role will involve turning offensive security expertise into autonomous agent capabilities, designing tools for probing and exploiting vulnerabilities, and managing LLM inference in production. This is a build role focused on engineering reliability, not research.

• Concevoir et faire évoluer la couche d'agent d'attaque, la partie du système qui décide quoi sonder, forme et teste des hypothèses, exploite et vérifie, sans faux positifs.
• Construire et faire évoluer l'armature de l'agent et l'orchestration qui transforme un LLM en un pentester autonome fiable, le cycle qui raisonne sur une application, forme des hypothèses d'attaque, agit et vérifie les résultats.
• Gérer l'inférence LLM en production : sélection du modèle, ingénierie des invites et du contexte, et maintien des coûts et de la latence sous contrôle.
• Strong instincts for prompt and context engineering, and the judgment to keep the model's job small and well-scoped
• Hands-on experience building LLM-powered applications or agents, tool use / function calling, structured outputs, multi-step orchestration, and the glue that makes it all hold together
• A track record of making LLMs reliable in production, you've wrestled nondeterminism, designed around model limitations, and shipped something that worked when it mattered
• Solid software fundamentals — testing, observability, and the discipline to keep a complex agent debuggable
• Ownership mentality, comfortable owning a critical, fast-moving subsystem end to end
• Real experience with evaluation: you've built or owned the harness that tells you whether a model or agent change is an improvement, not just a vibe
• 5+ years building production software, with strong Python
• Working knowledge of web application security, broken access control, IDOR/BOLA, SQLi, XSS, SSRF, SSTI, enough to collaborate fluently with offensive engineers
• Experience building eval harnesses or benchmarks specifically for agents (synthetic environments, CVE-based test targets, capture-the-flag-style scoring)
• Experience with agent frameworks, and strong opinions about when not to reach for one
• Familiarity with graph data models (e.g., Neo4j) for representing application state and attack context
• You've shipped an autonomous agent that did real, valuable work unattended in production, and you have scar tissue from making it trustworthy
• You've published or spoken on agent reliability, evaluation, or autonomous security tooling
• You've designed evaluation systems that actually drove improvement, closed the loop between "we changed something" and "it measurably got better."
• You pair an offensive-security mindset (CTF, bug bounty, pentesting, or research background) with the engineering chops to turn that intuition into a reliable system
• You have hands-on experience with agent fine-tuning or RL (SFT, GRPO, reward design for tool-using agents) and a grounded view of when it's worth it versus improving the harness