AI Security Researcher

AI Security Researcher to discover and defend against emerging threats to AI and machine learning systems.

Brampton, ON

Full time

Contract

Job description

The AI Security Researcher will investigate, discover, and mitigate novel security threats targeting AI and machine learning systems. This role sits at the frontier of adversarial ML, model exploitation, and AI red-teaming — producing original research that strengthens how organizations deploy, defend, and assure AI. The Researcher will design attacks and defenses, publish findings, and translate emerging threats into practical controls and evidence that buyers, sellers, and underwriters of AI can trust.

‍

Job responsibilities

Conduct original research on adversarial ML, model extraction, data poisoning, and prompt injection attacks.

Develop red-team methodologies and tooling for LLMs, agentic systems, and ML pipelines.

Evaluate model robustness, safety, and failure modes across the AI lifecycle.

Translate findings into defensive controls, benchmarks, and assurance evidence.

Contribute to AI risk frameworks (NIST AI RMF, ISO 42001, MITRE ATLAS).

Publish research, present at conferences, and advance the organization's technical authority.

Apply now

More open positions

Browse all open positions



PhD Research Student — ML Risk & Security

Doctoral research into quantifying and defending against machine learning risk.

Brampton, ON

Full time

Apply now