Adversarial Machine Learning Engineer - Red Teaming

About the role

We are looking for an individual contributor working 3 days a week to join an existing client team focused on Guardrails and AI red teaming for their foundation model suite. The role involves investigating edge-case vulnerabilities identified in campaign reports but not fully explained. The ideal candidate will design and train ML models and Small Language Models (SLMs) within a security context.

Responsibilities

• Conduct hands-on adversarial testing across the model, application, agentic layer, and data pipeline, including:
  • Multi-turn jailbreaks and guardrail bypass
  • Prompt injection
  • Agent and tool-chain misuse
  • Dangerous-capability evaluation
  • API abuse
  • Data poisoning, model inversion, and membership inference (where relevant)
• Investigate edge-case findings from AI red-team campaigns, transforming flagged anomalies into fully understood, reproducible vulnerabilities.
• Map severity-ranked findings to frameworks such as:
  • OWASP Top 10 for LLM Applications
  • NIST AI Risk Management Framework and its Generative AI Profile
  • MITRE ATLAS
  • EU AI Act Article 55 expectations
  with evidence and clean reproduction steps.
• Provide remediation guidance that is actionable and conduct retests to confirm fixes.
• Collaborate closely with the client’s Guardrails and AI red-teaming team to ensure findings are understood and acted upon.
• Translate technical findings into plain language for both engineers and non-technical stakeholders.
• Remain embedded with the team through remediation to verify fixes.

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 such as LoRA/QLoRA, PEFT, instruction tuning, and domain adaptation for performance and robustness.
• 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.

Benefits

• Fully remote work anywhere in the US, 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.

Schedule

3 days per week.