דרושים » אבטחת מידע וסייבר » AI Security Researcher

our company Cloud Security is seeking a Senior Security Researcher - AI Security to join our highly technical product research team working at the core of our cloud security platform. This is a rare opportunity to define a new discipline. AI security is an emerging field with few established playbooks, and you will help write them. In this role, you will own the research direction for AI security across our company's platform, uncovering novel risks in AI-native systems and translating that knowledge into product capabilities and industry-leading research. You'll be surrounded by experienced researchers and engineers who live and breathe security, with the space and backing to do original work in a domain that is rapidly evolving.
We're looking for an exceptional security researcher who can navigate ambiguity, think like an attacker, and bring clarity to a space that lacks it. You're curious, technically deep, and energized by the challenge of defining risk in systems that are still being understood.
Your Role:
Be at the forefront of an emerging discipline. Conduct technical analysis of AI frameworks, services, and architectures to discover novel risks, vulnerabilities, and attack vectors before they become industry-wide problems .
Define AI security risk by analyzing how exposure is created and exploited in AI systems. Collaborate with engineering and product teams to translate AI research into product findings.
Evaluate the risk of pre-trained models, vector databases, and orchestration frameworks (e.g., LangChain, LlamaIndex) to define how shadow AI creates organizational exposure.
Author blogs, whitepapers, and technical advisories that set the industry narrative. Present original research at leading conferences and serve as our company's external voice on AI risk topics.
Analyze AI systems from an attacker's perspective to define trust boundaries, map attack techniques, and identify exploitable paths. Translate findings into product features and outbound research.
Investigate and analyze AI infrastructures and services to find 0-day vulnerabilities, security holes, weaknesses, and design flaws.

our company Cloud Security is seeking a Senior Security Researcher - AI Security to join our highly technical product research team working at the core of our cloud security platform. This is a rare opportunity to define a new discipline. AI security is an emerging field with few established playbooks, and you will help write them. In this role, you will own the research direction for AI security across our company's platform, uncovering novel risks in AI-native systems and translating that knowledge into product capabilities and industry-leading research. You'll be surrounded by experienced researchers and engineers who live and breathe security, with the space and backing to do original work in a domain that is rapidly evolving.
We're looking for an exceptional security researcher who can navigate ambiguity, think like an attacker, and bring clarity to a space that lacks it. You're curious, technically deep, and energized by the challenge of defining risk in systems that are still being understood.
Your Role:
Be at the forefront of an emerging discipline. Conduct technical analysis of AI frameworks, services, and architectures to discover novel risks, vulnerabilities, and attack vectors before they become industry-wide problems .
Define AI security risk by analyzing how exposure is created and exploited in AI systems. Collaborate with engineering and product teams to translate AI research into product findings.
Evaluate the risk of pre-trained models, vector databases, and orchestration frameworks (e.g., LangChain, LlamaIndex) to define how shadow AI creates organizational exposure.
Author blogs, whitepapers, and technical advisories that set the industry narrative. Present original research at leading conferences and serve as our company's external voice on AI risk topics.
Analyze AI systems from an attacker's perspective to define trust boundaries, map attack techniques, and identify exploitable paths. Translate findings into product features and outbound research.
Investigate and analyze AI infrastructures and services to find 0-day vulnerabilities, security holes, weaknesses, and design flaws.

Were seeking a Senior Security Researcher to drive end-to-end research initiatives that strengthen detection capabilities. In this role, youll investigate emerging attack surfaces, craft and implement innovative detection logic, and test your findings in real-world environments. Its a hands-on position ideal for someone eager to transform research insights into effective, production-grade security defenses.
Responsibilities:
Research AI Agent and LLM-related risks, such as prompt injection and jailbreaking and implement sophisticated detection strategies.
Conduct research on cloud, web, and API security to uncover new threats and attack vectors.
Develop, refine, and design world-class detection logic and rules to enhance runtime protection.
Perform threat-hunting activities across large data sources to identify emerging attack patterns
Drive full-cycle research: from hypothesis and experimentation to production validation.
Collaborate with engineering and product teams to deliver actionable insights.

As the Code & AI Security Research Manager, you will lead an elite team in redefining trust for an era of agentic automation and hyper-connected supply chains. You will serve as a technical lighthouse and strategic leader, managing a high-performance team to secure the core of modern engineering. Your mission is to bridge deep technical research with product innovation, ensuring our customers' security posture evolves faster than the way they build software.
Key Responsibilities
Lead, mentor, and empower a team of world-class security researchers to pioneer AI-native security strategies.
Define the vision for identifying and mitigating novel attack vectors targeting coding agents and autonomous development workflows.
Oversee the evolution of traditional code vulnerabilities into proactive, self-healing workflows that fix issues before they reach a pull request.
Drive deep-dive research into software supply chain vulnerabilities, including CI/CD pipeline risks and third-party package security.
Proactively collaborate with Product and Engineering leaders to integrate research findings into core platform detection and remediation logic.
Establish the team as a global thought leader by overseeing original research publications, influential blog posts, and conference presentations.

: Were looking for a hands-on AI Cyber Intelligence Engineer - in the domain of attack surface. Someone who lives and breathes cyber security, loves exploring how attackers move through real environments, and is excited to shape how AI can automate and extend that process.
In this role, youll analyze real-world environments, identify potential attack vectors, and work closely with our AI engineering teams to translate your domain expertise into actionable, intelligent workflows. Youll play a key role in guiding how our platform learns to think and act like a top-tier security analyst.
The Responsibilities
Design and shape AI-driven security agents by encoding expert attacker and defender reasoning into agentic flows, prompts, decision logic, and investigative strategies.
Translate offensive security and red-team expertise into structured knowledge that enables AI systems to identify, prioritize, and reason about real-world attack paths in complex enterprise environments.
Model attacker behavior and multi-step attack scenarios, focusing on lateral movement, privilege escalation, and cross-domain exploitation - and guide how AI agents simulate and evaluate these scenarios.
Act as a domain expert partner for product and engineering teams, ensuring AI-driven security decisions remain grounded in real attacker tradecraft and operational reality.

we are seeking a hands-on and innovative Robotics Security Tech Lead / Senior Robotics Engineer to lead our Cyber-Physical / Embodied AI Security efforts. In this key role, you will bridge advanced security research and real-world robotics development, building and validating practical prototypes on real robots (HW/SW integration, sensors, communications, ROS/ROS2).
You will define and execute a research-to-demo roadmap that showcases realistic attack/defense scenarios and measurable security improvements for embodied AI systems. The role includes mentoring and leading student projects at university and collaborating closely with our company engineering and product teams to translate insights into deployable solutions.
Job Responsibilities
Lead the end-to-end research-to-prototype cycle for robotics/embodied AI security: ideation threat modeling PoC development validation demo readiness.
Build and maintain an experimentation platform for security evaluation on real robots
Investigate and mitigate threats across the embodied AI stack, including (high-level):
autonomy policy safety failures,
communications command authenticity,
software supply chain / update pipeline risks,
data protection privacy in real environments.
Design defense strategies and resilience mechanisms (monitoring, anomaly detection, guardrails, fail-safe behaviors, controlled recovery).
Lead and mentor student researchers at Reichman University: define projects, guide implementation, review results, and ensure research quality.
Produce clear technical documentation, evaluation reports, and demo artifacts for internal and external audiences.

We are a leading hybrid-cloud security company revolutionizing the way organizations manage cyber risk. We provide cutting-edge exposure management solutions by simulating real-world attack paths across cloud and on-prem environments. Our technology identifies misconfigurations, vulnerabilities, and identity exposures, allowing organizations to remediate risks with minimal effort. We are looking for a brilliant and motivated Product Management Intern to join our product team. This is a unique opportunity to sit at the intersection of Cybersecurity Research and Software Development, to add AI capabilities to the product. You wont just be watching. You'll be working with the Product group to brainstorm and TEST new AI-powered features for our platform.
Responsibilities:
* AI-driven research: use LLMs and AI tools to find better ways to explain and fix complex security issues. Use Python to analyze datasets and benchmark prompt performance to ensure AI accuracy in security contexts. Rapid Prototyping: Build functional Proof of Concepts (POCs) for AI Agents that automate complex security workflows. This includes enhancement to server-side attack simulation logic using Node.js, MongoDB.
* Work with Python and Node.js to develop innovative security solutions.
* Translate new cloud attack techniques into logic that our AI can simulate and explain.
* Collaborate with the development team to maintain and improve existing AI infrastructure.

In this role, you will be the architect of our "security brain." You will write the low-level code that observes what is happening (eBPF/Golang) and build the AI models that understand, diagnose, and prevent issues (LLMs/Python).
Key Responsibilities
1. The "Eyes": eBPF Development & Systems Engineering
Lead the Cimon Agent: Spearhead the active development of our high-performance eBPF agent "Cimon" using Golang and C.
Kernel-Level Innovation: Design and implement eBPF programs for deep observability, runtime security, and container monitoring.
Performance Obsession: Write beautiful, highly efficient code that runs in the Linux kernel with minimal overhead.
Community Leadership: Actively participate in the eBPF and open-source communities, contributing code and presenting technical deep dives at conferences.
2. The "Brain": AI Innovation & Security Research
AI-Driven Security Solutions: Architect and prototype models for:
Automated Exploitability: Checking SAST/SCA findings for validity.
AI Remediation: Automatically fixing Dockerfile misconfigurations and generating patches.
Model Detection: Identifying AI models embedded within codebases.
Benchmarking & Rigor: Design evaluation frameworks to measure model accuracy, false positives, and robustness in security contexts.
Prompt Engineering: Shape prompt strategies and workflows to translate real-world security challenges into actionable AI logic.
3. The Intersection: Collaboration & Evangelism
Cross-Functional Leadership: Serve as the technical link between the AI development team and the core security engineering team.
Thought Leadership: Author whitepapers, technical blogs, and deliver talks on the cutting edge of "AI for Systems Security."
Mentorship: Guide engineers on best practices for both low-level systems design and AI integration.
Why This Role?
No Context Switching Cost: You won't just be researching; you will be building the tools you research. You control the data collection (eBPF) and the analysis (AI).
Deep Tech Focus: This isn't a wrapper-API role. You will be dealing with kernel bypasses, memory safety, and LLM hallucinations all in the same week.
Impact: Your work will directly power the next generation of automated security remediation.

we are seeking a Threat Researcher to analyze enterprise environments and strengthen network resilience. This role focuses on researching device configurations, network relationships, and lateral movement opportunities, while developing methods and tools to harden infrastructures against advanced threats.
The ideal candidate will also support PoCs by applying research capabilities to real-world govermental environments and working closely with customers to validate threat scenarios and demonstrate cyber value.
The Responsibilities
Analyze various network devices, configurations, and security products
Implement methods and algorithms to discover network topology, relationships between devices, and potential lateral movement paths
Conduct network security assessments to identify weaknesses in customers' network infrastructure and recommend mitigations to monitor and limit unauthorized access
Develop research tools and frameworks to perform automatic analysis of network devices and security products
Research and analyze network-related cybersecurity threats and trends
Drive threat research efforts in customer and PoC environments to uncover, simulate, and validate real-world attack scenarios, demonstrating cyber value through our company Securitys platform capabilities
Translate technical research findings into actionable insights for customer-specific environments.
Work closely with other internal engineering and AI teams to integrate new capabilities into our platform and guide cross-product architectural decisions
Act as a security subject matter expert for multidisciplinary teams
Produce technical reports and research publications to share findings and methodologies.

We are looking for a Security Researcher who thrives on both sides of the fence. You will develop offensive tradecraft-discovering new attack vectors and writing exploits-then use that perspective to engineer robust, product-level mitigations. If youre energized by finding a novel browser attack on Monday and shipping the defense for it by Friday, this role is for you.
Key Responsibilities
Offensive Research: Discover new attack vectors, abuse patterns, and security gaps in browsers, web applications, OS internals, and enterprise workflows.
Defensive Engineering: Design and implement detections, mitigations, and security policies informed by your offensive findings; close the loop from attack to protection.
Vulnerability & Malware Analysis: Perform reverse engineering on malware, exploits, and obfuscated code across Windows, macOS, and browser environments.
Web & Browser Security: Research techniques ranging from classic vulnerabilities (XSS, SSRF) to browser-specific primitives (extension abuse, DOM manipulation, same-origin bypasses).
Supply-Chain Security: Investigate threats in software supply chains, including browser extension marketplaces and package registries.
Threat Intelligence: Correlate signals across multiple sources to identify malicious infrastructure and adversary TTPs.
Public Impact: Write technical blog posts, publish research, and represent Island at major security conferences (Black Hat, DEF CON, etc.).