Senior Staff ML Engineer, AI Safeguards - Moveworks

📋 Description

• Design, build and ship safeguards in the agent harness for prompt injection, single and multi-turn
• Build evals that measure safeguard efficacy on both false and true positives, using datasets from
• Work closely with our Security team: turn their adversarial findings into eval cases and fixes, and
• Select, integrate and fine-tune detection models within a stack shared by our commercial and
• Balance quality, latency and cost for controls that run in the request path
• Build configurable safeguard policies so customers can decide how sensitive topics are handled

🎯 Requirements

• Typically 8 or more years building production software, including 3 or more years of applied ML
• Hands-on experience developing safeguards for LLMs, such as guardrail models, content classifiers
• Strong model evaluation fundamentals for agent trajectories and text classification, and attention
• Working knowledge of how LLM safeguards get bypassed, including indirect prompt injection through
• Excellent Python Experience