11 hours ago
Coimbatore, IndiaStaff+
Responsibilities
- Author and maintain AI security threat models covering prompt injection, tool misuse, excessive agency, data exfiltration, memory poisoning, and cross-agent trust.
- Implement least-privilege, short-lived, auditable agent identities, scoped credentials, human approval gates, sandboxing, egress controls, and MCP tool-call policies.
- Build reusable input/output guardrails, data-leak filters, structured-output validation, safety evaluations, and regression tests for AI-enabled products.
- Lead AI penetration tests and adversarial campaigns against LLM features, agents, RAG pipelines, and MCP servers using manual techniques, automated attack agents, fuzzing, and external vendors.
- Secure AI models, datasets, dependencies, plugins, agent platforms, and model provenance through supply-chain controls and AI-BOM practices.
- Build and operate production security agents for vulnerability triage, exploitability analysis, finding validation, alert enrichment, incident evidence gathering, GRC evidence collection, and questionnaire response.
- Integrate AI security telemetry with detection pipelines, SOC workflows, MDR and AISOC tooling, Jira, and security assurance processes.
- Embed AI security evaluations, policy checks, and automated testing into the software development lifecycle.
- Own measurable technical and administrative security controls mapped to SOC 2, ISO 27001, NIST CSF 2.0, PCI DSS, NIST AI RMF, ISO/IEC 42001, and AIUC-1.
- Provide technical leadership during incidents and vulnerability surges, set standards, review designs, mentor engineers, and support customer AI security reviews and RFPs.
Requirements
- Six or more years of security engineering experience, including senior or equivalent scope, and at least two years of hands-on production experience securing LLM and agentic AI systems.
- Broad experience across AppSec, cloud, identity, vulnerability management, detection and response, and privacy engineering, with deep expertise in at least two areas.
- Track record of maturing technical and administrative controls across a high-growth SaaS organization.
- Hands-on depth in prompt injection, jailbreaks, tool and function calling, RAG and vector-store security, memory and context handling, MCP, agent protocols, and multi-agent trust boundaries.
- Expertise in end-to-end LLM and agentic AI penetration testing, adversarial testing, exploit chaining, remediation, and reproducible reporting.
- Mastery of the OWASP Top 10 for LLM Applications, OWASP agentic AI guidance, and MITRE ATLAS.
- Fluency with AI red-team tools and methods such as Garak, PyRIT, Promptfoo, or equivalent custom attack harnesses and evaluation suites.
- Experience building and operating AI agents or LLM-powered security tooling with measurable evaluation, guardrails, escalation paths, and audit trails.
- Strong Python skills for security tooling, automation, and adversarial testing, with comfort using APIs, CI/CD, and cloud-native environments.
- Hands-on experience with at least one AI security platform or LLM evaluation and guardrail framework.
- Working knowledge of NIST AI RMF and ability to translate security guidance into engineering controls.
- Sound judgment regarding OAuth, workload identity, secrets handling, least privilege, and scoped short-lived credentials for non-human actors.
- Preferred qualifications include agentic AI development, adversarial AI research, AI/ML CTF or bug-bounty results, open-source or standards contributions, PKI or machine identity experience, SOC automation, regulated B2B SaaS compliance programs, privacy or security certifications, and experience across US and India teams.
Benefits
- The company operates across India, North America, the United Kingdom, and Australia, with headquarters in New York City.
- AppViewX is an Equal Employment Opportunity Employer.
Tech Stack
Categories
About AppViewX
AppViewX builds enterprise software for automated certificate lifecycle management, PKI, and machine identity security delivered as SaaS and on‑premise. Its AVX Platform discovers and governs digital certificates and non‑human identities, automates renewals and access controls, and helps large organizations prove compliance. Founded in 2008 and headquartered in New York, the company is privately held with backing from Haveli Investments and is used by enterprises across financial services, healthcare, and technology.