Adversarial Machine Learning Engineer - Red Teaming

C-Serv; Canada; On-site; CAD 120,000 - 190,000; Full time

Benefits offered by this job

Fully remote Canada

Staff-level growth opportunities

Full-cycle hiring support

Values-led, woman-owned

Job summary

C-Serv in Canada seeks an Individual contributor to join an existing Guardrails and AI red-teaming client team. The role focuses on designing and training ML models and SLMs for security, performing hands-on adversarial testing across models, applications, and data pipelines.

You will translate findings into reproducible vulnerabilities, map them to established security frameworks, and deliver practical remediation with retests, while staying current on adversarial ML research and working

Qualifications

• Expert-level Python programming with ML frameworks (PyTorch, TensorFlow, Hugging Face).
• Hands-on ML model and SLM fine-tuning (LoRA/QLoRA, PEFT, domain adaptation).
• Strong ML math foundation: optimization, linear algebra, probability & statistics.
• Proven ability to design and execute adversarial attacks (evasion, data poisoning, model extraction).
• Experience implementing defenses (adversarial training, robust fine-tuning, differential privacy).
• Proficiency with adversarial ML toolkits (ART, CleverHans, Foolbox).
• Experience red-teaming AI/LLM systems (prompt injections, jailbreak testing).
• Threat-modeling skills; communicate risks to technical and non-technical stakeholders.
• Familiarity with MLOps practices (model versioning, experiment tracking, deployment).
• Active awareness of latest adversarial ML and GenAI security research.

Responsibilities

• Hands-on adversarial testing across model, app, and data pipeline (jailbreaks, prompt injections, API abuse).
• Translate findings into reproducible vulnerabilities with evidence and clean steps.
• Map findings to OWASP Top 10, NIST AI RMF, MITRE ATLAS, and EU AI Act expectations.
• Provide usable remediation guidance and perform retests to confirm fixes hold.
• Work shoulder to shoulder with client Guardrails and AI red-teaming teams; translate findings into plain language.
• Explain risks to engineers and non-technical stakeholders; ensure embedded engagement through remediation and retest.
• Stay updated on adversarial ML and GenAI security research; apply insights to client projects.
• Familiarity with MLOps and secure deployment pipelines; ensure versioning and tracking.
• Aim to grow into staff and principal-level technical influence within the client team.

Skills

Python programming

ML frameworks

LoRA/QLoRA

Adversarial attacks

Defenses

Red-teaming AI/LLM

Threat modeling

MLOps

Communication

Model evaluation

Tools

ART toolkit

CleverHans

Foolbox

PyTorch

TensorFlow

Hugging Face Transformers

Job description

We are looking for that Individual contributor, who will slot into an existing client team already running Guardrails and AI red teaming for their foundation model suite. The role digs into edge-case vulnerabilities that campaign reports surface but don't fully explain, the ideal candidate will be able to design and train ML models as well as SLM's in the security context.

What You'll Own

• Hands-on adversarial testing across the model, the application and agentic layer, and the data pipeline: multi-turn jailbreaks and guardrail bypass, prompt injection, agent and tool-chain misuse, dangerous-capability evaluation, API abuse, and, where relevant, data poisoning, model inversion and membership inference.
• Digging deeper into edge-case findings from AI red-team campaigns, turning a flagged anomaly into a fully understood, reproducible vulnerability.
• Severity-ranked findings mapped to 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, with evidence and clean reproduction steps.
• Remediation guidance that\'s actually usable, and a retest to confirm the fixes hold.

The Human Side of It

The testing is the craft. The trust is the job. Findings only matter if the right people understand and act on them.

• 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.

• 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 such as LoRA/QLoRA, PEFT, instruction tuning, and domain adaptation — for both performance and robustness objectives
• Strong foundation in ML mathematics: 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 such as 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 — 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

• Fully remote working anywhere in the 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.