CareerPlanSign in

Adversarial Machine Learning Engineer

Greater Vancouver, British Columbia💼 Full-time🗓 2026-04-21 → 2026-08-11

Core

Identifying vulnerabilities in LLM-driven systems, breaking model guardrails, and stress-testing AI deployments to ensure resilience before enterprise scale.

Role type

Adversarial Machine Learning Engineer (AI Red Team)

Builds

Hardened enterprise-scale AI products and resilient LLM systems

Domain

AI Security / Large Language Models / Enterprise Software

Deliverable

production ML models

Required skills

Adversarial ML, LLM security research, Prompt injection, Model jailbreak methodologies, AI system exploitation, Python, Custom attack tooling

Preferred skills

Cybersecurity background, Penetration testing, OWASP LLM Top 10 knowledge, Enterprise environment experience

Technologies

OpenAI, Anthropic, Open-source models, RAG architectures, Vector databases, API-based deployments

Responsibilities

Conduct adversarial testing across LLM systems, Execute attack simulations (prompt injection, jailbreaking, data exfiltration, model inversion), Develop automation scripts for attack scenarios, Analyse model behaviour under adversarial pressure, Identify vulnerabilities in APIs and embedding pipelines, Collaborate with engineering teams on remediation

Seniority

Mid-Senior, hands-on IC

Sourced via adzuna · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.