Hiring: AI Trust & Security Engineer

We are looking for an experienced AI Security Engineer to design, implement, and operationalize security controls across AI/ML, GenAI, and Agentic AI environments.

Key Responsibilities

- Design and implement preventive, detective, and corrective AI security controls across data, model, application, and runtime layers.
- Secure MLOps/LLMOps pipelines, model registration, artifact scanning, secrets, deployment gates, and continuous validation.
- Harden LLM applications, RAG pipelines, vector databases, model endpoints, APIs, notebooks, and AI infrastructure.
- Deploy and tune AI guardrails for prompt filtering, content safety, sensitive-data detection, output validation, and policy enforcement.
- Implement AI-SPM, model scanning, red teaming, prompt-injection detection, and runtime monitoring solutions.
- Secure IAM, RBAC, secrets, tokens, APIs, plugins, connectors, and agent tool access using least-privilege principles.
- Monitor and detect prompt attacks, jailbreaks, data exfiltration, unsafe outputs, policy violations, and abnormal agent behavior.
- Integrate AI security telemetry with SIEM/SOAR and enterprise monitoring platforms.
- Validate controls against prompt injection, jailbreaks, data leakage, insecure outputs, and unauthorized agent actions.
- Develop secure configuration baselines, operational runbooks, control libraries, and reusable AI security patterns.





Must-Have Skills
- 5+ years in Cybersecurity Engineering, Security Architecture, Platform Security, or Cloud Security.
- 2+ years in AI/ML Security, GenAI Security, LLM Security, or Secure AI Platforms.
- Robust knowledge of AI Security Controls, AI Trust Tooling, Runtime Guardrails, AI-SPM, and Secure AI Implementation.
- Hands-on experience with AWS, Azure, and/or GCP security.
- Experience with LLMs, RAG, vector databases, AI agents, model serving, MLOps/LLMOps, and AI APIs.
- Knowledge of Prompt Injection, Jailbreaks, Data Exfiltration, Model/Prompt Security, AI Red Teaming, DSPM, and Runtime Policy Enforcement.
- Experience with SIEM/SOAR, IAM, RBAC, secrets management, Kubernetes, API security, and cloud security.
- Strong understanding of agent security boundaries, connector governance, least privilege, input/output validation, grounding, and content safety.

Qualifications
- Bachelors/Masters degree in Computer Science, Cybersecurity, Engineering, Information Security, or related field.
- Certifications such as CISSP, CCSP, GIAC, cloud security, Kubernetes/security, or IAPP AIGP are preferred.
- Strong stakeholder communication and ability to translate security requirements into deployable, scalable controls.

Location: Delhi NCR , Pune , Mumbai , Bangalore , Kolkata Experience: 5+ Years | AI Security: 2+ Years

📌 AI Trust, Security Controls & Tools Implementation (Bengaluru)
🏢 SpanIdea
📍 Bengaluru