AI Security Agent Engineer

Orcapod Consulting Services; Chennai District; On-site; INR 2,500,000 - 5,000,000; Full time

Job summary

Orcapod Consulting Services is seeking an experienced AI Security Agent Engineer to secure Generative AI, LLMs and ML platforms. You will focus on security architecture, threat modeling, guardrails and secure AI/ML pipelines, with emphasis on cloud security across AWS/Azure/GCP.

The role involves AI red teaming, prompt injection defense, CI/CD integration and development of security telemetry for AI interactions. 7–12 years in cybersecurity/AI security is preferred, with strong Python skills.

Qualifications

• 7–12 years of experience in Cybersecurity / AI Security / ML Security.
• Hands‑on experience in AI Security and LLM/GenAI Security.
• Knowledge of MITRE ATLAS and OWASP Top 10 for LLMs.
• Experience with AI Red Teaming / Adversarial Testing / Prompt Injection / Jailbreaking.

Responsibilities

• Design and implement security controls for Generative AI, LLMs, AI Agents and ML pipelines.
• Perform AI threat modeling and security architecture reviews using MITRE ATLAS / STRIDE.
• Conduct AI Red Teaming and adversarial testing, including prompt injection and jailbreaking.
• Implement AI security guardrails, input/output sanitization and policy controls.
• Integrate security testing, vulnerability scanning and container security into CI/CD and MLOps pipelines.
• Develop security telemetry, monitoring and anomaly detection for AI/LLM interactions.
• Implement secure configuration, IAM, secrets management and cloud security controls.

Skills

AI Security

LLM Security

GenAI Security

Python

DevSecOps

MLOps

AWS

Azure

GCP

Tools

PyRIT

Garak

PromptFoo

ART

Job description

Role: AI Security Agent Engineer
Experience: 712 Years
Employment Type: C2H (Contract-to-Hire)
Location: [Location]

Job Summary:
We are looking for an experienced AI Security Agent Engineer with strong expertise in securing Generative AI, LLMs, AI Agents and ML platforms. The candidate will work on AI security architecture, threat modeling, red teaming, guardrails, secure AI/ML pipelines and cloud security.

Key Responsibilities:

• Design and implement security controls for Generative AI, LLMs, AI Agents and ML pipelines.
• Perform AI threat modeling and security architecture reviews using MITRE ATLAS / STRIDE.
• Conduct AI Red Teaming and adversarial testing, including prompt injection and jailbreaking.
• Implement AI security guardrails, input/output sanitization and policy controls.
• Integrate security testing, vulnerability scanning and container security into CI/CD and MLOps pipelines.
• Develop security telemetry, monitoring and anomaly detection for AI/LLM interactions.
• Implement secure configuration, IAM, secrets management and cloud security controls.

Required Skills:

• 7–12 years of experience in Cybersecurity / AI Security / ML Security.
• Strong hands‑on experience in AI Security and LLM/GenAI Security.
• Knowledge of OWASP Top 10 for LLMs/GenAI and MITRE ATLAS.
• Experience in AI Red Teaming / Adversarial Testing / Prompt Injection / Jailbreaking.
• Hands‑on experience with PyRIT, Garak, PromptFoo or ART.
• Strong Python skills.
• Experience with DevSecOps / MLOps / Secure CI/CD.
• Cloud Security experience in AWS / Azure / GCP.
• Knowledge of Terraform/Bicep, IAM, secrets management and secure configuration.

Good to Have:

• Azure OpenAI / Azure AI Studio / Vertex AI / AWS Bedrock.
• MLflow / Kubeflow / LangChain / LlamaIndex.
• AI Supply Chain Security / SBOM / AIBOM.
• NIST AI RMF / ISO 42001 / EU AI Act.
• CISSP / CCSP / Cloud Security certifications.

Key Skills:
AI Security, LLM Security, GenAI Security, AI Red Teaming, Adversarial Testing, OWASP LLM, MITRE ATLAS, AI Guardrails, Python, DevSecOps, MLOps, AWS, Azure, GCP.

9685741994