Senior Manager- AI security architect Guardrail Engineering - GO/JC/4887/2026

Golden Opportunities; Pune District; On-site; INR 900,000 - 1,500,000; Full time

Job summary

Golden Opportunities in India seeks a Senior Manager to lead AI security engineering initiatives across the country. You will drive security strategy, oversee integration of AI security tools, and establish secure CI/CD practices to protect AI workloads.

The role requires 10+ years in security engineering with 3+ years in AI/ML security, plus hands-on experience with prompt injection and RAG security. Office-based, Pan India, with substantial impact.

Qualifications

• Must have 10+ years in Security Engineering or App Security.
• 3+ years in AI/ML Security, AI Red Teaming, or AI Tool Development.
• Production-level Python development.
• Hands-on integration or extension of at least two AI security tools.
• Experience with prompt injection, indirect prompt injection, and jailbreak attacks.
• RAG pipeline security including data exfiltration and embedding inversion.
• Adversarial testing of agentic AI systems including tool abuse and privilege escalation.
• Strong knowledge of OWASP LLM Top 10 and MITRE ATLAS.
• Experience integrating security testing stages into CI/CD pipelines.

Skills

Python production

AI security

Prompt injection

Agentic AI testing

RAG security

CI/CD security

OWASP LLM Top 10

MITRE ATLAS

Security tool integration

Education

Bachelor's degree

Tools

Garak

PyRIT

LLM Guard

Presidio

NeMo Guardrails

Lakera Guard

LangGraph

LangChain

Job description

Candidate Expectations

Total Experience and Relevant Experience: 10-15 Years

Job Details

Job Title: Senior Manager

Job Location: Pan India

Work Model: Work from Office

Candidate Expectations

Total Experience and Relevant Experience: 10-15 Years

Candidate Location: Anywhere in India

Skills- AI security architect, LLM, Langgraph, Open AI, cloud security, OWASP, MITRE ATLAS and Threat modelling

Education and Certification

Qualification: Bachelor’s degree

Detailed Job Description

Key Skills

• Hands-on development experience with the ability to write and ship production Python, with TypeScript or Go experience preferred.
• Direct experience integrating or extending at least two AI security tools such as Garak, PyRIT, LLM Guard, Presidio, NeMo Guardrails, Lakera Guard, or equivalent tools.
• Practical experience executing prompt injection, indirect prompt injection, and jailbreak attacks against real LLM applications in red team, research, or CTF environments.
• Experience with RAG pipeline security, including retrieval-based data exfiltration, embedding inversion, vector store poisoning, and related defense patterns.
• Experience with agentic system adversarial testing, including agent loop hijacking, tool abuse, and privilege escalation in multi-agent orchestration frameworks.
• Solid understanding of OWASP LLM Top 10 and MITRE ATLAS, with the ability to map TTPs to concrete adversarial test cases.
• Experience integrating security into CI/CD pipelines such as GitHub Actions, Azure DevOps, or Jenkins by building security pipeline stages.
• A strong sense of ownership, desire to create meaningful outcomes, and passion for work that serves a greater good for customers, communities, or global challenges.
• Experience developing SIEM detection logic for AI workloads, including Sigma rules, KQL, or SPL queries for AI-specific anomaly detection.
• IaC security experience, including writing or reviewing Terraform or Bicep modules with security controls encoded.

Mandatory Skills:

10+ years of experience in Security Engineering or Application Security, including 3+ years in AI/ML Security, AI Red Teaming, or AI Security Tool Development; production-level Python development; hands-on integration or extension of at least two AI security tools such as Garak, PyRIT, LLM Guard, Presidio, NeMo Guardrails, or Lakera Guard; practical experience with prompt injection, indirect prompt injection, and jailbreak attacks; RAG pipeline security, including data exfiltration, embedding inversion, and vector store poisoning; adversarial testing of agentic AI systems, including tool abuse and privilege escalation; strong knowledge of OWASP LLM Top 10 and MITRE ATLAS; and experience integrating security testing stages into CI/CD pipelines using GitHub Actions, Azure DevOps, or Jenkins.

Good to Have Skills:

Experience developing AI-specific SIEM detection rules using Sigma, KQL, or SPL; Terraform or Bicep security modules; hands-on knowledge of LangChain, LangGraph, LlamaIndex, or Semantic Kernel; AI security research, publications, CVE disclosures, or conference presentations; enterprise security engineering or red-team experience; and the ability to communicate adversarial findings to senior stakeholders and collaborate with development teams to implement security mitigations.