Description:

Individual contributor role working 3 days a week within a client team focused on Guardrails and AI red teaming for foundation models.
Responsible for hands-on adversarial testing, analyzing edge-case vulnerabilities, and providing remediation guidance.

Requirements:

Expert-level Python programming and proficiency in ML frameworks (PyTorch, TensorFlow, Hugging Face Transformers).
Experience fine-tuning ML models and Small Language Models (SLMs) with techniques like LoRA/QLoRA and instruction tuning.
Strong foundation in ML mathematics (optimization, linear algebra, probability, statistics).
Proven ability to design and execute adversarial attacks and implement defenses.
Familiarity with adversarial ML toolkits (ART, CleverHans, Foolbox) and red-teaming AI/LLM systems.
Strong threat-modeling skills and ability to communicate risks to both technical and non-technical stakeholders.

Fully remote work opportunity within the US, focused on delivery rather than presence.
Clear growth path to staff and principal-level technical influence.
Full support from C-Serv throughout the hiring process and beyond.
Values-led, woman-owned company emphasizing empathy, integrity, collaboration, and growth.

Skills