Sign up with

Already have an account? Log in here

Need some help?
Talk to us at +91 7670800001

Innovation Security Researcher – AI Agents & NHI at Astrix Security

Tel-Aviv, Tel-Aviv District, Israel -

Full Time

Start Date

Immediate

Expiry Date

04 Apr, 26

Salary

0.0

Posted On

04 Jan, 26

Experience

5 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Security Research, AI, Cloud Systems, SaaS, Analytical Skills, Technical Analysis, Communication Skills, Prototyping, Product Development, Ecosystem Analysis, Risk Mapping, Innovation, Deep Learning, Technical Prototypes, Threat Modeling, Vulnerabilities

Industry

Computer and Network Security

Description

Astrix is looking for an Innovation Security Researcher to lead frontier exploration in the AI Agents and NHI ecosystem: uncovering new security risks and opportunities, dissecting emerging platforms and competitors, and turning research into concrete outcomes like POCs and technical prototypes that shape our product direction and market leadership. About the role Lead groundbreaking research in uncharted territory for AI agents and NHI in Cloud and SaaS systems Explore and analyze emerging agent architectures, behaviors, abuse and security patterns, mapping risks and opportunities before they become mainstream Conduct deep product and ecosystem landscape analysis to guide innovation Translate research into concrete deliverables - POCs, technical prototypes, threat models, vulnerabilities, and product recommendations that drive roadmap impact Partner closely with Product and Engineering to turn findings into scalable product capabilities and customer value Work with Marketing to produce market leadership content and support conference submissions as research matures Requirements Strong background in security research for modern cloud / SaaS systems, with a proven ability to find high-signal insights Deep curiosity and exposure to AI and LLM ecosystems Ability to thrive in ambiguity and independently drive research from idea to outcome with high independence, ownership and strong judgment Proven ability to create concrete outputs (POCs, prototypes, structured analysis) that validate ideas and shape product direction Strong analytical skills, including the ability to perform deep technical analysis and synthesize findings into clear recommendations Strong English communication and writing skills, with the ability to produce clear technical outputs for internal and external audiences

Responsibilities

Lead research in AI agents and NHI ecosystems, identifying security risks and opportunities. Translate findings into POCs and prototypes that influence product direction.