Experience: 6-10 Years
Location: Hyderabad, India (On-site)

Role Overview
We are looking for an AI Security Engineer with a strong foundation in both Artificial
Intelligence and Cyber Security. This role focuses on building secure AI systems,
protecting LLM-based applications, and embedding security across the entire AI lifecycle,
from data to deployment.

Key Highlights
● Work hands-on with LLMs and Generative AI use cases with a strong security focus
● Design and secure RAG-based intelligent applications
● Implement secure vector databases and semantic search systems
● Drive AI security across MLOps and DevSecOps pipelines
● Opportunity to build and scale secure AI solutions in production environments

Required Skills & Qualifications:
● 5+ years of experience in Python development
● Strong experience with frameworks like Django, Flask, or FastAPI
● Hands-on expertise in AWS cloud services (EC2, Lambda, S3, RDS, ECS, etc.)
● Strong understanding of microservices and distributed systems
● Experience with relational and NoSQL databases (PostgreSQL, MySQL, MongoDB, DynamoDB)
● Proficiency with Git and version control practices
● Experience with CI/CD pipelines and automation tools

Must-Have Skills
● Strong proficiency in Python
● Hands-on experience with Large Language Models (LLMs)
● Strong background in Cyber Security / Information Security domain
● Understanding of application security, cloud security, and network security fundamentals
● Experience with RAG architecture and secure data pipelines

● Knowledge of Machine Learning fundamentals

● Understanding of Deep Learning frameworks (PyTorch / TensorFlow)
● Experience with vector databases / semantic search concepts Security-Specific Expertise

Strong knowledge of:
● OWASP Top 10 / API Security Top 10
● Secure coding practices
● Authentication & Authorization (OAuth2, JWT, SSO)

Experience in identifying and mitigating:
● Prompt Injection Attacks
● Data Leakage & Sensitive Data Exposure
● Model Poisoning / Adversarial Attacks
● Insecure Output Handling in LLMs

Hands-on experience with:
● Vulnerability Assessment & Penetration Testing (VAPT)
● Threat Modeling (STRIDE / MITRE ATT&CK)

Understanding of:
● Encryption (data at rest & in transit)
● Secrets management (Vault, KMS, etc.)
● Identity & Access Management (IAM)

Good to Have
● Experience with Hugging Face, LangChain, or similar frameworks
● Familiarity with AI security frameworks (e.g., OWASP Top 10 for LLMs)
● Experience in cloud security (AWS / Azure / GCP)
● Knowledge of Docker, Kubernetes, CI/CD security
● Exposure to DevSecOps practices
● Experience with SIEM tools (Splunk, ELK, etc.)
● Understanding of compliance frameworks (ISO 27001, SOC2, GDPR)

Core Focus Areas

● Securing LLM-powered applications (chatbots, Q&A, summarization tools)
● Protecting RAG pipelines and data retrieval systems
● Implementing secure semantic search and AI-driven retrieval
● Designing AI threat detection and response mechanisms
● Ensuring secure model deployment, monitoring, and governance

Responsibilities
● Design and implement secure AI/ML architectures
● Perform AI security assessments, threat modeling, and VAPT
● Build and enforce LLM guardrails and security controls
● Collaborate with engineering teams to embed security-by-design principles
● Monitor and respond to AI-specific and cyber security threats
● Ensure compliance, governance, and risk management for AI systems

To apply for this job please visit forms.gle.