Job Description

Responsibilities :

Roles & Responsibilities: 1. Programming and scripting expertise, especially in Python, and preferably experience in other languages like C, C++, Java, or JavaScript. 2. Deep understanding of AI/ML concepts, model training pipelines, and AI attack surface areas including fairness, bias, and anomaly detection. 3.Knowledge of security testing standards and frameworks such as OWASP (including OWASP LLM Top 10), MITRE ATLAS, NIST AI security guidelines. 4.Proficiency with common penetration testing tools like Kali Linux, Burpsuite, Nmap, Nessus, and familiarity with AI-focused frameworks such as Clever Hans, ART, Fool box or similar. 5. Proficient in emerging AI security threats and offensive security techniques, including real-world adversarial tactics and prompt injection methods. 6. Familiarity with cloud platforms (AWS, Azure, GCP) and cloud security. 7. Design clear, actionable technical reports and presentations targeting both technical and business stakeholders. 8. Lead red teaming operations with a focus on AI system security, simulating attacks to evaluate defenses. 9. Tool Expertise: Rocket Software, IBM X-Force Red, NetSPI, Secragon, REXX, Standard Pen test suite (Kali Linux, Burpsuite, Nessus, Metasploit).

Soft skills: 1. Strong at client communications, Stakeholder management. 2. Experience in managing remote teams of 3+ and ability to prepare dashboards and report status and issues with Client directly. 3. Strong analytical and problem-solving skills, with the ability to think critically and identify creative solutions. 4. Excellent communication and collaboration skills to work effectively with cross-functional teams

Preferred Certifications: 1. OSCP, GPEN, GWAPT, CEH, or AI security-focused credentials.