Adversarial Machine Learning Engineer - Red Teaming

C-Serv

8d • Remote

About The Position

We are looking for an Individual Contributor who will integrate into an existing client team focused on Guardrails and AI red teaming for their foundation model suite. This role involves investigating edge-case vulnerabilities identified by campaign reports that lack complete explanations. The ideal candidate will possess the ability to design and train both Machine Learning (ML) models and Small Language Models (SLMs) within a security context.

Requirements

• Expert-level Python programming with deep proficiency in ML frameworks such as PyTorch, TensorFlow, and Hugging Face Transformers.
• Hands-on experience fine-tuning ML models and Small Language Models (SLMs), including techniques like LoRA/QLoRA, PEFT, instruction tuning, and domain adaptation, for both performance and robustness objectives.
• Strong foundation in ML mathematics, including optimization, linear algebra, probability, and statistics.
• Proven ability to design and execute adversarial attacks, including evasion (adversarial examples), data poisoning, model extraction, and membership inference.
• Experience implementing defenses such as adversarial training, robust fine-tuning, input sanitization, and differential privacy.
• Proficiency with adversarial ML toolkits like Adversarial Robustness Toolbox (ART), CleverHans, and Foolbox.
• Experience red-teaming AI/LLM systems, including prompt injection, jailbreak testing, and safety/alignment evaluation.
• Ability to evaluate and benchmark model robustness, safety, and security posture before and after fine-tuning.
• Familiarity with MLOps practices, including model versioning, experiment tracking, and secure deployment pipelines.
• Strong threat-modeling skills and an attacker's mindset, with the ability to communicate risks clearly to technical and non-technical stakeholders.
• Active awareness of the latest adversarial ML and GenAI security research.

Nice To Haves

• Works shoulder to shoulder with the client's Guardrails and AI red-teaming team, not at a distance from them.
• Translates findings into plain language: technical depth for the engineers, a clear risk picture for anyone less hands-on with the model itself.
• Stays embedded well past the first findings, through remediation, to the retest that proves it's fixed.

Responsibilities

• Conduct hands-on adversarial testing across the model, application, and agentic layers, as well as the data pipeline. This includes multi-turn jailbreaks, guardrail bypass, prompt injection, agent and tool-chain misuse, dangerous-capability evaluation, API abuse, and, where relevant, data poisoning, model inversion, and membership inference.
• Investigate edge-case findings from AI red-team campaigns, transforming flagged anomalies into fully understood and reproducible vulnerabilities.
• Provide severity-ranked findings mapped to industry standards such as the OWASP Top 10 for LLM Applications, the NIST AI Risk Management Framework and its Generative AI Profile, MITRE ATLAS, and EU AI Act Article 55 expectations, complete with evidence and clear reproduction steps.
• Develop actionable remediation guidance and conduct retesting to confirm the effectiveness of implemented fixes.

Benefits

• Fully remote working anywhere in Canada, built around delivery rather than presence.
• A clear path to grow into staff and principal-level technical influence.
• Full support from C-Serv across the hiring process and beyond, with full-cycle accountability.
• A values-led, woman-owned delivery partner built on empathy, integrity, collaboration, and growth.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed