דרושים » אבטחת מידע וסייבר » AI Research Engineer, Security

As an AI Security Researcher , you will play a key role in shaping the future of modern runtime AI security. You will investigate how real-world attacks unfold across AI-enabled applications, agents, tools, executed in cloud environments, and turn those insights into innovative, production-grade security capabilities across our AI Security Posture Management (AI-SPM) and AI Detection & Response (AI-DR) products.

This role is ideal for a deeply technical researcher who is driven to understand AI attacks at their core - not just identify suspicious prompts or surface-level indicators. You will research how prompt injection, tool misuse, agent drift, model abuse, and other emerging AI attack techniques translate into real runtime behavior and security impact. You will then apply that knowledge to build protections that are precise, resilient, scalable, and grounded in how attacks actually work in production.

Specifically, you will:

Research real-world attacks targeting models, agents, MCP/tooling ecosystems, RAG applications, and AI-enabled production systems.
Drive research end-to-end - explore, design, develop, validate, and deploy detection logic and protections based on runtime telemetry, exploit PoCs, technical analysis, and threat intelligence.
Shape AI-SPM capabilities by identifying what telemetry, signals, and modeling are required to continuously discover AI components, classify AI behavior, map risk, and detect unsafe or anomalous usage in production.
Shape AI-DR capabilities by researching how to detect AI-driven attacks, prove runtime impact, establish causality, and distinguish failed attempts from real compromise.
Work closely with engineering and product teams to turn deep technical research into practical security capabilities that deliver clear customer value.

We're looking for a Security Researcher to join our team at the intersection of security research, AI, and product. This isn't a traditional research role - you'll be deeply embedded in how the platform is built, working side by side with R&D, Product, and AI teams to make sure security expertise is baked into every layer of what we ship. You'll own detection and analytics research across cloud, identity, endpoint, and beyond, while actively shaping how AI capabilities are applied to solve real security problems at scale.





WHAT YOU WILL DO

Research and develop sophisticated detections and behavioral analytics across multiple security landscapes - cloud, identity, endpoint, network, and application - with a focus on coverage that scales across customer environments.
Work closely with R&D, Product, and AI teams as the security authority - reviewing features, shaping designs, and ensuring security logic is sound, practical, and impactful.
Apply an AI-native approach to detection and analytics challenges - leveraging LLMs, ML signals, and AI-assisted workflows to do things that rule-based approaches can't.
Identify gaps in detection coverage and analytical capabilities, and drive those findings directly into the product roadmap.
Analyze real-world attacker techniques and translate them into detection logic, hunting content, and analytical frameworks that ship as part of the platform.
Evaluate detection quality rigorously - measuring fidelity, coverage, and performance against real attacker behavior and production telemetry.
Stay sharp on the evolving threat landscape and rapidly incorporate new techniques, campaigns, and attacker tooling into our detection library.
Contribute to external research output - blog posts, talks, open-source tooling - that reflects our depth and point of view in the security community.

As a Security Researcher , you will play a key role in shaping the future of modern runtime and AI security. You will investigate how real-world attacks unfold across applications and cloud environments, and turn those insights into innovative, production-grade security capabilities.

This role is ideal for a deeply technical researcher who is driven to understand attacks at their core - not just identify surface-level indicators. You will research exploitation chains, runtime behavior, attacker techniques, and emerging AI attack patterns, then apply that knowledge to build protections that are precise, resilient, scalable, and grounded in how attacks actually work.

Specifically, you will:

Research real-world attack techniques targeting modern applications, cloud-native environments, and AI-driven systems.
Design, develop, validate, and deploy detection algorithms based on technical research, large-scale runtime telemetry, threat intelligence, and exploit PoCs.
Shape the strategy for detection data collection by defining the required telemetry, collection points, and data quality standards needed to support effective protection.
Drive research efforts end-to-end, from initial exploration and technical investigation to production-grade protection capabilities for active threats.
Work closely with engineering and product teams to turn research into practical security capabilities.

We're looking for a Senior Applied AI Scientist to sit at the frontier of AI security - turning emerging threats into the detection models that protect how AI is used inside the world's largest organizations. You'll be part of the AI Security Research department, working hand-in-hand with security researchers to translate threat intelligence into trainable signals that catch malicious behavior and security risks across the AI-powered workflows of Fortune 500 companies.

You'll bring deep technical versatility - reaching for classical ML, deep learning, or agentic based approaches based on what the problem demands, and the evaluation rigor to know when a model is truly ready for the real world. If you want to define what AI security engineering looks like, not just practice it, this role is for you.

What Youll Do
Responsibilities:
Build, train, and ship detection models end-to-end, from raw data to production.
Choose the right method for each problem - traditional ML, deep learning, fine-tuned LLMs, agents or heuristics - based on theoretical insights turned into practical results.
Partner with security researchers to turn security research outputs and domain expertise into detection capabilities.
Own evaluation: design benchmarks, build labeled datasets, and define production standards.
Monitor models in production across all paradigms - ML, deep learning, LLM-based, and agentic systems to track degradation and ensure reliability
Iterate fast, with a tight feedback loop between model performance and product outcomes.

We're looking for a talented Applied Security Researcher to join our team and play a major role in our frontier research team, enabling contextual code understanding across complex cloud deployments.
WHAT YOU'LL DO
Investigate the Code, Cloud, and AI technologies that we integrate with and protects, answering key research questions to unlock new features and product areas.
Design and build high-quality functional prototypes, driving abstract product ideas from inception into working PoCs and supporting development teams through initial implementation.
Conduct technical research to model risks and attack vectors specific to modern cloud- and AI-native architectures and systems.
Define and implement novel agentic workflows and advanced methods to express consistent contextual understanding of evolving application and cloud environments.

we are looking for a Senior Security Analyst to join our research team. In this role, you will help uncover critical security risks in cloud, SaaS, and AI environments, with a strong focus on AI Agents & Non-Human Identity (NHI) Security.

You will own hands-on security research across active customer POCs, conducting deep-dive security research on their environments, identifying vulnerabilities, surfacing real risks, and delivering clear remediation steps. Utilizing cutting-edge platform alongside hands-on manual research, you will translate complex security gaps into high-impact insights and executive reports, helping shape the way organizations secure machine and AI-driven identities at scale.

What We Do
The Frontier of Identity Security: a pioneering startup in the AI Agent & Non-Human Identity (NHI) security space.
Research-Driven Value: Our team focuses on IAM security across cloud, SaaS, and GenAI/AI Agent infrastructures, working hands-on with customer environments.
Customer Journey Partners: Analysts play a critical role in POCs, uncovering misconfigurations and building actionable Security Reports that move deals and guide customers toward a stronger security posture.
Cross-Functional Impact: Youll bridge the gap between technical research and business value, collaborating with Product, Engineering, and Sales to drive product enhancements and help close strategic deals.
Your Responsibilities
Lead Security Research in POCs: Conduct hands-on security analysis of customer environments using platform, manual techniques, and advanced AI tools to optimize your research workflow.
Manual Environment Analysis: Deep-dive into customer architectures using APIs, access keys, and to expose weaknesses in IAM, machine identities, and AI agent permissions.
Deliver Actionable Insights: turn complex findings into high-level, impactful Security Reports that outline significant risks and provide clear, step-by-step remediation guidance.
Drive Product & Sales Excellence: Collaborate with Product and Engineering teams to share insights from the field and help improve the platform.
Partner with Sales teams to review environmental reports and confidently present security findings to customer stakeholders.
Stay Ahead of the Curve: Continuously track emerging risks in cloud security trends, IAM vulnerabilities, and emerging threats related to AI agents and automation.

We are seeking an AI Security Researcher to join Dashs core research team. Youll investigate how AI agents - spanning coding agents, SaaS AI platforms, cloud, and endpoints - can be abused, and design detections that stop threats before they cause impact. Each platform is different, yet they share common risk patterns across prompts, tools, MCP servers, skills, hooks, identity, and data movement. Your mission is to master both: uncovering unique attack surfaces while building universal, session- and intent-aware defenses. This role combines deep platform research, responsible security testing, and close collaboration with engineering to translate findings into production runtime protection. You will help define the field of Agentic Security.
Responsibilities:
Research agentic threats: Prompt injection, tool/plugin/MCP abuse, skill and hook misuse, rogue autonomy, identity misuse, data leakage, adversarial AI, and protocol exploitation across coding agents and enterprise AI platforms.
Develop runtime detections: Design detections for multiple environments (coding agents, SaaS AI, cloud, endpoints), leveraging platform hooks, APIs, telemetry, and native guardrails where available.
Analyze platform complexities: Deep-dive into architectures, permissions, workflows, and agent capabilities (MCP servers, Skills, plugins, extensions) while extracting cross-platform risk patterns.
Build scalable detection logic: Prototype and refine heuristics, signatures, and intent-aware detectors that hold up at enterprise scale with low friction for builders.
Investigate monitoring and enforcement boundaries: Push what platforms allow for visibility and control - hooks, plugins, configuration surfaces, inventory signals, and policy enforcement points.
Prototype PoCs: Validate attack paths end to end, then turn findings into production-ready signatures, heuristics, detectors, and runtime policies.
Collaborate with engineering: Embed research into Dashs detection pipelines, session-aware runtime protection, and policy/governance modules.
Stay ahead of the field: Track adversarial AI and agent security research, continuously evolving Dashs detection and enforcement coverage.

Were looking for an experienced Vulnerability Researcher to help us uncover how modern AI tools, agents, and enterprise environments can be abused - and turn those findings into impactful security research.
This role combines deep technical research with real industry impact.
Youll investigate emerging attack techniques, build proof-of-concepts, publish research the security community cares about, and help shape how our company protects customers.
Were looking for someone who loves understanding how things work, thinks creatively like an attacker, and knows how to turn technical findings into research people actually want to read and talk about.
What Youll Do
Research vulnerabilities and attack techniques across AI tools, endpoints, browsers, MCP servers, extensions, and enterprise environments
Investigate real-world threats, CVEs, supply-chain attacks, and AI-related security risks
Build proof-of-concepts and demonstrations of new attack paths
Publish technical research, blog posts, and security content.
Work closely with Product and Engineering to improve our companys detection and prevention capabilities
Help position our company as a leading company in AI security research
Explore new technologies and identify risks before they become mainstream

We are hiring an AI Researcher to join the research team building the next generation of AI-native security systems. You will work alongside security and threat researchers to build large-scale AI agents that reason over software, code, endpoint activity, and security signals to detect malicious behavior, uncover vulnerabilities, assess risk, and make autonomous security decisions in real-world production environments. We are entering the Mythos era - where attackers operate at machine speed using autonomous systems and AI-generated software, and defenders must evolve the same way. We use state-of-the-art frontier models, including access to Mythos, to build reliable AI-native security systems at global scale. You will help design the evaluations, harnesses, and reliability infrastructure that make autonomous agents dependable under real customer load, while collaborating with leading AI organizations including Anthropic on initiatives such as Glasswing. This is an opportunity to work at the frontier of AI, autonomous systems, and cybersecurity while helping define how the next generation of security systems will operate.
Key Responsibilities
Build AI agents and autonomous security systems that reason over software, code, endpoint activity, MCPs, and security signals to detect malicious behavior, uncover vulnerabilities, and assess risk at production scale.
Develop systems, tooling, and infrastructure that enable agents to autonomously investigate threats, hunt for malware in massive datasets, and operate reliably in complex security environments.
Design and run experiments to evaluate frontier-model and agent capabilities in realistic adversarial scenarios, including benchmark creation, large-scale datasets, automated evaluations, and human-in-the-loop review systems.
Build the evaluation harnesses, observability systems, and reliability infrastructure required to make autonomous agents accurate, scalable, and dependable under real customer load.
Engineer for scale and performance across large distributed AI systems, including inference optimization, orchestration, batching, caching, cost controls, and graceful degradation under high demand.
Continuously evaluate emerging models, agent architectures, prompting techniques, and research directions to ensure our systems remain at the frontier of AI-native cybersecurity.
Rapidly prototype and test new approaches across reasoning, autonomy, evaluations, and security workflows as the AI landscape evolves.
Partner closely with threat and security researchers to extract domain expertise, translate analyst reasoning into AI workflows, and enable new forms of automation and autonomous investigation.
Collaborate with leading AI and security researchers to shape the future of AI-native cybersecurity as the industry transitions into the Mythos era.
Senior candidates will help define research direction, shape technical strategy, identify high-leverage problems, and influence how autonomous AI systems are deployed across the organization.

As an AI Engineer at our company, you will own the intelligent decision-making pipelines that turn complex workspace telemetry into autonomous security actions. You will design, build, and deploy the autonomous reasoning workflows and advanced data classification systems that drive our company's preventive operating model. Your focus will be on creating resilient, production-grade AI systems capable of deep policy comprehension, real-time prevention at the point of adoption, and autonomous remediation of existing risks.
This is a ground-floor opportunity to shape the AI strategy of a fast-growing cybersecurity company alongside a lean, elite team of builders.
WHAT YOULL DO
End-to-End Ownership: Own our AI capabilities entirely from initial research, architectural design, and prototyping, through to production deployment, optimization, and continuous monitoring.
Design & Build Agentic Workflows: Architect multi-step AI agents capable of autonomously investigating workspace risks, interpreting complex enterprise policies, and taking precise remediation actions.
Integrate Multi-Faceted ML: Bring innovation and creative thinking to our core engine. Implement diverse ML models across our entire research and product pipeline-utilizing clustering, text extraction, document analysis, and tabular data classification.
Ship Production-Grade AI: Build high-throughput, resilient, and fault-tolerant production code. You will ensure our AI pipelines and agentic workflows are highly predictable, deeply observable, and built to scale under enterprise-grade loads.
Implement Guardrails & Evaluation: Build continuous evaluation frameworks to benchmark agent accuracy, mitigate hallucinations, and enforce strict data security/privacy guardrails.