Senior AI Security Researcher

At AppViewX, our values reflect how we work together in practice—not just what we aspire to. They show up in everyday decisions, how we collaborate across teams, and how we treat each other while building and delivering our work. If these values resonate with you, you’ll likely feel at home here.
• Clarity: We interact with transparency, simplicity, and shared purpose.
• Unity: We build unity through mutual respect, trust, and collaboration.
• Innovation: We stay curious, challenge assumptions, and drive continuous improvement.
• Speed: We act with urgency, focus, and follow-through to deliver results fast.
• Precision: We bring accuracy, consistency, and care to everything we do.

We are looking for an experienced AI Security Researcher to lead deep technical research for the Agent Identity Security (AIS) platform.

This research-focused role continuously explores the evolving AI and Agentic AI security landscape and translates findings into actionable security intelligence, prototypes, technical recommendations, and thought leadership for AIS.

The researcher will focus on AI agents, Agentic AI frameworks, MCP and emerging agent protocols, LLM security, AI identity, tool security, AI supply-chain risks, prompt and context security, and AI governance standards. The role will also continuously evaluate competitive products and emerging technologies to identify new threats, capabilities, and opportunities relevant to AIS.

A critical responsibility of this position is to serve as an independent security research function for AIS, continuously challenging the platform architecture, integrations, gateways, policy enforcement mechanisms, and agent interactions to ensure AIS remains secure as the AI ecosystem evolves.

The ideal candidate combines a strong security research mindset with hands-on technical ability and can move from research → threat hypothesis → experimentation → PoC → security recommendation → product influence → publication.

• Lead AI Security Research: Conduct continuous research into emerging threats across LLMs, AI agents, autonomous systems, Agentic AI platforms, MCP servers, AI tools, models, AI gateways, and AI development environments.
• Research Agentic AI Attack Surfaces: Identify and analyze vulnerabilities involving prompt injection, indirect prompt injection, tool poisoning, excessive agency, insecure tool execution, privilege escalation, credential exposure, data exfiltration, memory poisoning, context manipulation, agent impersonation, and cross-agent attacks.
• Research AI Identity Security: Investigate security challenges associated with human-to-agent, agent-to-agent, agent-to-tool, agent-to-MCP-server, and agent-to-model identities, including authentication, authorization, delegation, impersonation, credential management, and non-human identities.
• Evaluate Emerging AI Protocols: Research new protocols and standards supporting AI and autonomous agents, including Model Context Protocol (MCP), Agent-to-Agent (A2A) protocols, agent communication standards, tool protocols, identity standards, and emerging interoperability frameworks.
• Build Research PoCs: Develop working proof-of-concepts for emerging AI protocols, frameworks, security controls, attack techniques, and defensive mechanisms to validate their relevance to AIS.
• Perform Adversarial Security Research: Build controlled attack scenarios against AI agents, MCP servers, tools, models, and gateways to understand realistic attack paths and determine how AIS should detect, prevent, or govern them.
• Continuously Test AIS Security: Independently evaluate AIS architecture, APIs, agent integrations, MCP Gateway, policy enforcement, hooks, SDKs, credentials, authentication flows, and other security-sensitive components for potential weaknesses.
• Drive Security-by-Research for AIS: Identify security gaps before they become customer or production risks and provide engineering teams with clear technical findings, attack scenarios, severity assessments, and recommended mitigations.
• Perform Competitive Security Analysis: Continuously research competing and adjacent products across AI security, AI governance, AI-SPM, MCP security, identity security, cloud security, and Agentic AI security.
• Maintain Competitive Intelligence: Compare competitor capabilities, architectures, security approaches, integrations, research publications, patents, product releases, and positioning against AIS and identify opportunities for technical differentiation.
• Track Emerging Threats: Monitor security research, vulnerabilities, CVEs, attack techniques, academic publications, security conferences, open-source projects, and industry developments relevant to AI and Agentic AI.
• Research AI Security Standards: Track and evaluate standards and frameworks including OWASP Top 10 for LLM Applications, OWASP Agentic AI guidance, MITRE ATLAS, NIST AI RMF, ISO/IEC 42001, AIUC-1, and other emerging AI security and governance standards.
• Map Research to AIS Capabilities: Translate newly identified attack techniques and security risks into potential AIS posture checks, policies, detections, risk indicators, compliance mappings, and security controls.
• Create White Papers: Author technically rigorous white papers covering AI security threats, Agentic AI security, MCP security, AI identity, governance, emerging protocols, attack techniques, and AIS security approaches.
• Publish Technical Research: Produce security advisories, technical blogs, research reports, attack demonstrations, architecture recommendations, and other technical thought-leadership content.
• Develop Threat Models: Create and continuously evolve threat models for AI agents, MCP ecosystems, AI gateways, models, tools, credentials, memory systems, RAG pipelines, and autonomous workflows.
• Create AI Security Taxonomies: Develop reusable classifications for Agentic AI threats, attack techniques, vulnerabilities, identities, security controls, and defensive mechanisms.
• Collaborate with Engineering and Product: Present research findings to architects, engineering teams, security teams, and product management and help translate validated research into future AIS capabilities.
• Support Customer Security Discussions: Provide deep technical expertise for strategic customer discussions, security workshops, research briefings, and complex questions around AI and Agentic AI security.
• Represent AIS Research: Contribute to external technical communities through research papers, responsible disclosures, standards discussions, conference submissions, technical demonstrations, and open-source initiatives where appropriate.

• 4+ years of cybersecurity experience, with significant experience in security research, application security, cloud security, offensive security, identity security, vulnerability research, or related disciplines.
• Demonstrated research experience in AI/ML security, LLM security, Agentic AI security, application security, identity security, or emerging cybersecurity technologies.
• Strong understanding of LLMs, AI agents, Agentic AI frameworks, RAG systems, tools/functions, memory, context management, AI gateways, and model APIs.
• Hands-on knowledge of MCP and emerging AI/agent protocols, with the ability to independently build clients, servers, integrations, attack scenarios, and security PoCs.
• Strong understanding of AI attack techniques including prompt injection, tool poisoning, data exfiltration, insecure output handling, excessive agency, memory manipulation, supply-chain attacks, and privilege escalation.
• Strong knowledge of authentication, authorization, OAuth/OIDC, API security, IAM, workload identities, secrets, tokens, credentials, RBAC/ABAC, and zero-trust principles.
• Strong hands-on programming capability in Python, with the ability to rapidly build research tools, attack simulations, protocol implementations, automation, and PoCs.
• Experience with security testing and research tools across web applications, APIs, cloud infrastructure, containers, identity systems, and distributed applications.
• Familiarity with major AI ecosystems and platforms such as OpenAI, Anthropic, Microsoft Copilot, Google Gemini, AWS Bedrock, Claude Code, Cursor, GitHub Copilot, Salesforce Agentforce, and other emerging agentic platforms.
• Knowledge of security and AI frameworks such as OWASP, MITRE ATT&CK/ATLAS, NIST AI RMF, ISO/IEC 42001, and emerging Agentic AI security standards.
• Ability to independently read and analyze research papers, specifications, protocol definitions, standards, open-source implementations, and security advisories and determine their relevance to AIS.
• Strong technical writing skills with demonstrated ability to produce white papers, research reports, vulnerability reports, technical blogs, threat models, or academic publications.
• Experience performing competitive technical analysis and converting findings into actionable recommendations for engineering and product teams.
• Strong analytical mindset with the ability to challenge assumptions, formulate attack hypotheses, design experiments, and validate findings through reproducible research.
• Ability to work independently on ambiguous and emerging security problems where established security patterns or industry standards may not yet exist.
• Published security research, CVEs, responsible disclosures, patents, academic papers, conference presentations, open-source security tools, or contributions to security/AI standards are strongly preferred.

We will measure success primarily by research impact rather than feature delivery. Expected outcomes include:

• Identification of new AI and Agentic AI attack techniques relevant to AIS.
• Research-backed recommendations that improve the security architecture of AIS.
• Working PoCs for emerging AI protocols, threats, and defensive techniques.
• New security posture checks, policies, detections, or controls proposed from validated research.
• Regular competitive intelligence identifying technical gaps and differentiation opportunities.
• High-quality white papers, technical publications, threat models, and research reports.
• Identification and responsible remediation of security weaknesses within AIS.
• Contributions to industry discussions, standards, open-source initiatives, patents, or original security research.
• A continuously maintained AIS AI Security Research Roadmap covering emerging protocols, threats, standards, competitors, and research priorities.

AppViewX caters to a wide range of customers from Fortune 1000 companies, including six of the top ten global commercial banks, five of the top ten global media companies, and five of the top ten managed healthcare providers. Over the years, we grew our diverse team, perfected our automation platform, and expanded our global footprint to India, North America, United Kingdom, and Australia. Today, we are headquartered in New York City and have come a long way by optimizing opportunities to create lasting relationships with enterprises, gaining unshakable customer trust along the way.

AppViewX is proud to be an Equal Employment Opportunity Employer. It is AppViewX’s policy to afford equal employment opportunities to all employees regardless of race, color, national origin, ancestry, religion, citizenship status, gender, gender expression or identity, sexual orientation, age, marital status, military or veteran status, pregnancy, disability, genetic information, arrest record, or other protected class under state, federal, or local law.