Who we are Moveworks: the Agentic AI Assistant platform that empowers the entire workforce. Our platform enables employees to converse with all of their business systems through natural language to quickly find answers and automate tasks. Backed by Greylock and Sequoia.
About the role
We approach our distributed world of work with flexibility and trust. Work personas (flexible, remote, or required in office) are categories that are assigned to ServiceNow employees depending on the nature of their work and their assigned work location. Learn more here . To determine eligibility for a work persona, ServiceNow may confirm the distance between your primary residence and the closest ServiceNow office using a third-party service. Found on 1752vc Careers, the job board for startup and VC roles.
What they're looking for
- Typically 8 or more years building production software, including 3 or more years of applied ML (training, evaluating and deploying models in production systems)
- Hands-on experience developing safeguards for LLMs, such as guardrail models, content classifiers, prompt injection or jailbreak detection, or safety evals
- Strong model evaluation fundamentals for agent trajectories and text classification, and attention to the quality of training and evaluation data
- Working knowledge of how LLM safeguards get bypassed, including indirect prompt injection through tools and documents, and multi-turn jailbreaks
- Excellent Python Experience
More about this role
• Design, build and ship safeguards in the agent harness for prompt injection, single and multi-turn jailbreaks, toxicity and sensitive topics, and sensitive data exposure
• Build evals that measure safeguard efficacy on both false and true positives, using datasets from customer reports, adversarial testing and production traffic
• Work closely with our Security team: turn their adversarial findings into eval cases and fixes, and build mitigations together that hold when detection misses
• Select, integrate and fine-tune detection models within a stack shared by our commercial and government environments
• 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
• Monitor safeguard behavior in production and fix regressions
• Typically 8 or more years building production software, including 3 or more years of applied ML (training, evaluating and deploying models in production systems)
• Hands-on experience developing safeguards for LLMs, such as guardrail models, content classifiers, prompt injection or jailbreak detection, or safety evals
• Strong model evaluation...
Browse similar: AI jobs · AI startup jobs · Startup jobs · San Francisco Bay Area