Senior AI Security Engineer

Senior AI Security Engineer

Location: Remote
Compensation: ₹3.28 LPM
Employment Type: Contractor Assignment
Engagement Duration: 4 Weeks
Experience Required: 5+ Years
Work Commitment: Full-time (40 hours/week) or Part-time (20 hours/week)
Time Zone Requirement: Minimum 4 hours of overlap with PST

About the Role

We are seeking an experienced Senior AI Security Engineer to evaluate the effectiveness of Static Application Security Testing (SAST) tools in identifying vulnerabilities within Generative AI (GenAI) applications.

The role involves building and testing small, runnable AI agent and Retrieval-Augmented Generation (RAG) codebases containing realistic security vulnerabilities, particularly Sensitive Information Disclosure (SID) and Excessive Agency (EA).

You will develop vulnerable, fixed, and near-miss code variants, analyze security findings, validate results through testing, and document root causes and recommended security controls.

Key Responsibilities

• Build runnable AI agent and RAG repositories containing realistic vulnerabilities across tool calling, memory, and Model Context Protocol (MCP).
• Develop vulnerable, fixed, and hard-negative code variations with minimal security-relevant differences.
• Analyze and annotate source-to-sink paths, data flows, action paths, security controls, and root causes.
• Identify and assess Sensitive Information Disclosure and Excessive Agency vulnerabilities.
• Define authorization contexts, trust boundaries, and access control requirements.
• Develop deterministic tests to validate vulnerable, fixed, and negative scenarios.
• Evaluate security findings and recommend appropriate mitigation strategies.
• Participate in security calibration, documentation, and peer review.

Required Qualifications & Skills

• Minimum 5+ years of experience in Application Security, Product Security, or Security-focused Software Engineering.
• Strong experience in secure code reviews and vulnerability assessment.
• Hands-on knowledge of source-to-sink analysis, taint analysis, and SAST tools such as CodeQL or Semgrep.
• Practical experience building LLM agents or RAG applications using:
• LangChain
• LlamaIndex
• OpenAI / Anthropic SDKs
• Model Context Protocol (MCP)
• Strong understanding of authorization concepts, including OAuth, IAM, identity management, trust boundaries, multi-tenancy, and document-level access controls.
• Production-level programming experience in Python and/or TypeScript.
• Ability to distinguish genuine security vulnerabilities from false positives and non-findings.

Good to Have

• Knowledge of OWASP Top 10 for LLM Applications and GenAI security risks.
• Experience with MCP security and AI agent threat modeling.
• Background in security evaluations, vulnerability research, or AI application security testing.

Engagement & Compensation

• Compensation: ₹3.28 LPM
• Duration: 4 weeks
• Work Type: Remote contractor assignment
• Commitment: Full-time (40 hours/week) or Part-time (20 hours/week)
• PST Overlap: 4 hours mandatory
• Benefits: This is a contractor assignment and does not include medical benefits or paid leave.

Selection Process / Vetting

Candidates will undergo the following evaluation stages:

• ICF (Initial Competency/Technical Evaluation): Assessment of relevant technical knowledge and practical expertise.
• Profile Review: Evaluation of professional experience, technical background, and relevant project exposure.

Both stages are mandatory for shortlisted candidates.

Who Should Apply?

This opportunity is ideal for experienced Application Security Engineers, Product Security Engineers, AI Security Engineers, and Security-focused Software Developers who have hands-on experience securing LLM-powered applications, AI agents, and RAG systems.

Interested candidates are encouraged to apply with an updated resume highlighting relevant AI security, LLM, SAST, and application security experience.

Pay: From ₹328,000.00 per month

Experience:

• Cybersecurity Expert: 4 years (Required)

Work Location: Remote