Company Overview:

T D Newton is a specialized technology firm focused on building robust, secure, and scalable AI infrastructure for enterprise-level applications. Operating at the intersection of advanced machine learning and cybersecurity, the company provides sophisticated security frameworks that protect large-scale language models and automated decision-making systems. Headquartered in Navi Mumbai, T D Newton serves a global clientele, ensuring that high-stakes AI deployments remain resilient against evolving adversarial threats.

Role Overview:

As an AI Red Team Engineer, you will be at the forefront of identifying and mitigating vulnerabilities within complex AI and machine learning ecosystems. You will work closely with data scientists, security architects, and product teams to stress-test models, simulate adversarial attacks, and develop defensive strategies that safeguard our proprietary AI platforms. Your contributions will directly influence the integrity and reliability of our systems, ensuring that our clients can deploy cutting-edge technology with complete confidence in its security posture.

Key Responsibilities:

- Execute rigorous penetration testing on LLMs and generative AI models to identify potential prompt injection, data leakage, and model manipulation vulnerabilities.

- Develop and implement automated security testing frameworks to continuously monitor model behavior and detect anomalies in real-time.

- Conduct deep-dive security research into emerging adversarial techniques to proactively harden our AI infrastructure against sophisticated attack vectors.

- Collaborate with cross-functional engineering teams to integrate security-by-design principles into the AI development lifecycle, minimizing risks before deployment.

- Analyze security telemetry and logs to provide actionable insights that improve the overall resilience and performance of our security analytics platforms.

Required Skillset:

- Must have 5+ years of demonstrated hands on experience covering Development, Offensive Security, Red Teaming, Penetration Testing, AppSec, Al/ML Security.

- Proven expertise in designing and running adversarial attack simulations.

- Hands-on experience with Al Security, adversarial ML techniques, LLM vulnerabilities, and Agentic Al architectures.

- Demonstrated expertise in AI/ML testing methodologies, specifically focusing on the security evaluation of large language models and neural networks.

- Proven ability to perform comprehensive penetration testing and vulnerability assessments within complex software environments.

- Strong proficiency in security analytics, with the capability to translate complex data patterns into effective defensive strategies.

- Excellent communication skills, with the ability to articulate technical security risks to non-technical stakeholders and influence cross-departmental security policies.

- A solid academic foundation in Computer Science, Cybersecurity, or a related quantitative field, reflecting a strong grasp of algorithmic security.

- High level of adaptability and comfort working in an on-site environment at our Navi Mumbai office, collaborating effectively within a fast-paced, high-stakes engineering team.