S R.

Key Skills

Software

Other

AWS SageMaker

Top Subject Matter

AI security testing and CI/CD automation for vulnerability correlation

Red teaming and vulnerability assessment for ML/AI systems

Top Data Types

Computer Code Programming

Top Task Types

RLHF

Red Teaming

Freelancer Overview

Security-focused AI correlation automation within CI/CD to improve assessment accuracy. Brings 15+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Other. Education includes Master of Business Administration, Academy Europe Open University (2024) and Bachelor of Science, University of Saskatchewan (2015). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including RLHF and Red Teaming.

Labeling Experience

Application Security Manager - Accenture

AWS SageMakerRed Teaming

As an Application Security Manager, you lead application and security architecture efforts across a consulting environment. You use penetration testing, threat modeling, and vulnerability correlation to improve the security posture of networks, systems, databases, and applications. You also drive security awareness and adversary emulation initiatives using industry frameworks and standardized testing methods. • Set up data security controls using AWS KMS encryption and AWS Certificate Manager (ACM). • Conducted full-scope Red Team assessments and adversary emulation mapped to MITRE ATT&CK. • Delegated and managed least-privilege access across AWS accounts using IAM cross-account roles. • Developed security awareness training programs that reduced security incidents by 80%.

2022 - Present

Security-focused AI correlation automation within CI/CD to improve assessment accuracy

RLHF

Automated AI-driven correlation filters into the CI/CD pipeline to support AI-related security testing and reduce false positives. The work involved integrating model/security findings correlation behavior into an automated workflow rather than manual review. This enabled more accurate identification of relevant signals for downstream remediation and training/assessment loops. • Integrated automated AI-driven correlation filters into CI/CD. • Reduced false-positive rates by about 40%. • Improved mean time to remediation for identified issues. • Supported continuous assessment using automated correlation results.

2020 - Present

Adversarial red-teaming of ML models for AI vulnerability identification

OtherRed Teaming

Performed adversarial testing and red-teaming on ML models to identify vulnerabilities such as prompt injection, data poisoning, and model evasion. Conducted security-focused evaluation of AI model behaviors to discover weaknesses that could be exploited. Communicated and acted on findings to reduce risk ahead of deployment. • Tested ML models against prompt injection, data poisoning, and model evasion. • Used red-teaming methodology to surface AI/ML weaknesses. • Informed security improvements based on adversarial outcomes. • Contributed to lowering critical vulnerabilities prior to release.

2022 - 2022

Application Security Lead - Geotab

AWS SageMakerRed Teaming

As an Application Security Lead, you oversee vulnerability management and penetration testing activities across teams. You manage security for virtual infrastructure environments and design least-privilege access models for critical systems. You also mentor engineers and communicate detailed Red Team findings to improve overall cyber resilience. • Led the Vulnerability Management Program and coordinated penetration testing and remediation. • Managed security and virtual infrastructure in VMware and enforced access control policies. • Reduced OWASP Top 10 critical backlogs through directed remediation efforts by 90% in 6 months. • Mentored a team of 10 AppSec engineers and developers on secure coding and security awareness.

2017 - 2019

Education

Work History