Senior Agentic AI Developer

Senior Agentic AI Developer

Engineering | Tel Aviv | Senior | Full-time

About the Role

We are a cutting-edge cybersecurity research and R&D group building a next-generation platform at the intersection of Agentic AI, malware analysis, and threat intelligence.

Our work focuses on designing and developing highly secure, on-premises systems for restricted and air-gapped environments, where reliability, explainability, and deep technical accuracy are critical.

This role is not about integrating existing tools — you will own the architecture, design, and implementation of a complex, multi-layered system from the ground up, remaining fully hands-on.

What You’ll Do

• Own the end-to-end architecture of a multi-component system combining LLM pipelines, agent orchestration, and malware analysis engines
• Design and implement agentic AI systems leveraging LLMs, autonomous agents, and multi-agent frameworks (ReAct-style or similar)
• Integrate AI capabilities into low-level reverse engineering workflows, including binary analysis, debugging, and sandbox environments
• Lead fine-tuning and adaptation of models on domain-specific data such as malware samples, behavioral telemetry, and threat intelligence feeds
• Build systems for air-gapped / on-prem environments, including secure model lifecycle, update mechanisms, and strict data isolation
• Translate research concepts into production-grade systems that are scalable, reliable, and interpretable
• Drive technical excellence across outputs such as feature extraction pipelines, detection logic, and system architecture
• Ensure explainability and consistency of AI-driven outputs, including human-readable analysis of complex behaviors

Requirements

• 5+ years of experience in software engineering, with ownership of complex system architecture
• Strong hands-on experience with low-level programming (C++ required, Rust is a strong advantage)
• Deep expertise in reverse engineering, including manual and automated techniques
• Proven experience working with LLMs / ML pipelines, including fine-tuning and production deployment
• Experience with multi-agent systems / autonomous agents / orchestration frameworks
• Background in applying ML to security-related data (binary analysis, network traffic, threat intelligence, etc.)
• Experience designing systems for restricted / air-gapped environments
• Ability to work end-to-end: architecture → implementation → debugging
• Strong ownership, problem-solving mindset, and ability to drive complex, ambiguous challenges
• High attention to detail and focus on accuracy and interpretability

Why Join

• Work on hard, unsolved problems at the intersection of AI and cybersecurity
• Build systems from scratch with full ownership and real impact
• Collaborate with a team of top-tier engineers and researchers
• Influence the architecture and direction of a deep-tech product in its early stages