Senior Staff ML Engineer, AI Safeguards - Moveworks
Core
Design, build, and ship safeguards in the agent harness for prompt injection, jailbreaks, toxicity, sensitive topics, and data exposure.
Role type
Senior Staff ML Engineer (AI Safeguards)
Builds
Safeguards, evals, detection models, and configurable policies for an Agentic AI Assistant platform.
Domain
Enterprise AI / LLM Safety
Deliverable
production ML models
Required skills
Python, LLM safeguard development, model evaluation, adversarial testing, prompt injection detection, multi-turn jailbreak detection, fine-tuning, latency optimization, policy configuration
Preferred skills
Experience with guardrail models, content classifiers, safety evals, indirect prompt injection mitigation
Technologies
Python, LLM stacks, production ML systems
Responsibilities
Design safeguards for prompt injection and jailbreaks; Build evals to measure efficacy; Integrate and fine-tune detection models; Balance quality, latency, and cost; Build configurable safeguard policies; Monitor production behavior and fix regressions
Seniority
Senior Staff, hands-on IC
