AI Security Architect

ConveGenius; Dadri; On-site; INR 3,000,000 - 6,000,000; Full time

Benefits offered by this job

Health insurance

Job summary

ConveGenius is seeking an AI Security Architect to lead security strategy, governance, risk management, and safe deployment of AI systems across platforms. The role requires deep cybersecurity expertise at the intersection of AI security and traditional security, with hands‑on experience in cloud, containers, and API security.

You will define hardening measures for AI infrastructures, establish threat modelling, and build provenance controls while driving security from 0 to 1 in a fast‑paced

Qualifications

• Strong experience securing AI, ML, and LLM‑based apps in production.
• Deep understanding of AI threat modeling, prompt injection, data poisoning, adversarial attacks.
• Knowledge of OWASP LLM Top 10 and AI security best practices.
• Experience conducting AI security assessments, red teaming, and vulnerability reviews.
• Understanding of model governance and secure AI deployment.
• Hands‑on cybersecurity across cloud, app, and infrastructure layers.

Responsibilities

• Define enterprise AI security strategy for LLMs, ML models, and AI infrastructure.
• Lead AI threat modelling including adversarial attacks and data poisoning.
• Secure AI training and inference infrastructure and API security.
• Run AI red‑team initiatives to test LLM and agentic systems in production.
• Develop AI governance frameworks with risk management and audit trails.
• Ensure secure deployment across cloud, containers, and API layers.

Skills

AI security

Threat modeling

OWASP LLM Top 10

Red teaming

Cloud security

SIEM/SOC

Governance

Secure deployment

Model provenance

Job description

Does working for 150+ million children of Bharat excite you?

Then this opportunity is for you!

About us

ConveGenius is an AI-native education infrastructure company transforming how governments, enterprises, and social institutions deliver learning and governance outcomes at population scale. Operating across B2G and B2B segments, the company partners with state governments, CSR funders, philanthropies, and social enterprises to build intelligent education ecosystems that are both impactful and commercially sustainable.

At its core, ConveGenius runs two synergistic business lines:

• SwiftAI – the intelligence and automation layer that powers citizen engagement, governance efficiency, and real‑time decision‑making for governments and institutions.
• SwiftSchool – the learning infrastructure layer that integrates adaptive learning, digital classrooms, and analytics to drive measurable student and system outcomes.

This dual‑engine model enables ConveGenius to serve as the technology backbone for education reform — connecting classrooms, communities, and command centres through a unified AI‑powered framework. Unlike traditional edtech companies that deliver content, ConveGenius builds infrastructure — platforms that integrate deeply into public delivery systems while enabling private and philanthropic partners to scale their missions with measurable results.

With operations across 22+ Indian states and partnerships with multilaterals, CSR alliances, and government departments, ConveGenius has established itself as a partner‑friendly enterprise trusted for aligning policy priorities with social and financial returns. Supported by institutional investors and guided by a double bottom line philosophy, the company consistently delivers impact at scale and profitability with purpose.

As ConveGenius enters its next phase of growth, it is shaping the future of AI‑led public education infrastructure — where technology, partnerships, and governance intelligence converge to redefine how nations learn and thrive.

Role Overview: As the AI Security Architect, you will lead the security strategy, governance, risk management, and safe deployment of AI, LLM, ML, and agentic systems across platforms. You will define how AI systems are hardened against adversarial attacks, how AI infrastructure is secured end‑to‑end, and how AI governance frameworks are operationalised across engineering and product teams. Strong cybersecurity engineering experience is required — this role sits at the intersection of AI security and traditional cybersecurity, and the right candidate must bring depth in both. This role is part of a 0‑to‑1 vertical build. The person joining should be comfortable with ambiguity, high ownership, rapid iteration, hands‑on execution, team building, and periods of high‑intensity work during the early setup phase.

Key Responsibilities

• Define and own the enterprise AI security strategy covering LLMs, ML models, agentic systems, and AI infrastructure.
• Conduct AI threat modelling: adversarial attacks, model inversion, data poisoning, prompt injection, model extraction.
• Secure AI training and inference infrastructure: model serving hardening, API security, pipeline integrity.
• Lead AI red‑team initiatives: systematic adversarial testing of LLM and agentic systems in production.
• Build AI governance frameworks: model risk management, provenance controls, audit trails, and approval workflows.
• Secure agentic systems and orchestration layers: tool‑use security, agent permission models, sandboxing strategies.
• Define model integrity and provenance controls: signing, versioning, reproducibility, and tamper detection.
• Conduct AI security assessments and vulnerability reviews across all production AI systems before and after deployment.
• Establish secure AI deployment practices ensuring platform security across cloud infrastructure, containers, and API layers.
• Implement privacy‑preserving architectures (data masking, synthetic data, differential privacy) to safeguard corporate PII from leaking into LLM training sets or context windows.
• Embed automated security compliance scanners, vulnerability checks, and input/output guardrails directly into the MLOps CI/CD pipelines.

Must‑Have Skills

• Strong experience securing AI, ML, and LLM‑based applications in production environments.
• Deep understanding of AI threat modeling, prompt injection, jailbreaks, data poisoning, and adversarial attacks.
• Strong knowledge of OWASP LLM Top 10 and AI security best practices.
• Experience conducting AI security assessments, red teaming, and vulnerability reviews.
• Understanding of model governance and secure AI deployment.
• Strong hands‑on cybersecurity experience across cloud, application, and platform security — including penetration testing, vulnerability management, SIEM/SOC experience, or security architecture at the infrastructure layer.
• AI Ecosystem Knowledge is a must. Conceptual clarity on transformer architectures, fine‑tuning pipelines (SFT/RLHF), and vector search mechanics.

What We Offer and Why You Should Join ConveGenius

• Work with a diverse and passionate team spread across India, bringing together people from different backgrounds, perspectives, and expertise.
• Be part of an organization with a strong on‑ground presence across more than two thirds of India, giving you exposure to large scale, real world impact.
• Play a meaningful role in strengthening the education ecosystem and contributing directly to learning outcomes for millions of children.
• Gain experience working at the intersection of education, technology, and public systems, building skills that are highly relevant and future‑focused.
• Work in a culture that values ownership, learning, and collaboration, with space to take initiative and grow professionally.
• Enjoy stability and peace of mind with employee friendly benefits, including health insurance coverage and other supportive policies.
• If you are driven by purpose, enjoy solving complex problems, and want your work to create visible impact, ConveGenius offers a place to grow while making a difference.