Senior Staff ML Engineer, AI Safeguards - Moveworks
ServiceNowMountain View, CALIFORNIA, United StatesOn-Site
Needs a free Superjobs account. You'll finish on ServiceNow's SmartRecruiters page.
Skill score
Summary
This Senior Staff ML Engineer builds and ships safeguards for the Moveworks agent harness, including prompt injection, jailbreak, toxicity, and sensitive data detection, and measures their effectiveness with evals. The role suits a senior applied ML engineer with production LLM safety experience who can balance quality, latency, and cost in request-path controls.
- Function
- Data Science
- Estimated salary
- Est. $207k–311k/yr
- Estimated for a staff-level role, ~8 yrs experience, United States. Not published by the employer.
- Work mode and location
- On-Site, Mountain View, CALIFORNIA, United States
- Experience
- 8+ yrs
- Employment type
- Full-time
Job description
Roles and responsibilities
- 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
Skills required
Top skills
- Production software development
- Applied machine learning
- LLM safeguards
- Prompt injection detection
All skills (6)
- Jailbreak detection
- Model evaluation
- Agent trajectory evaluation
- Text classification
- Python
- Fine-tuning detection models
Qualifications
- 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
Other details
For positions in this location, we offer a base pay of $201,300 - $352,300, plus equity (when applicable), variable/incentive compensation and benefits. Sales positions generally offer a competitive On Target Earnings (OTE) incentive compensation structure. Please note that the base pay shown is a guideline, and individual total compensation will vary based on factors such as qualifications, skill level, competencies and work location. We also offer health plans, including flexible spending accounts, a 401(k) Plan with company match, ESPP, matching donations, a flexible time away plan and family leave programs.
Compensation is based on the geographic location in which the role is located and is subject to change based on work location.
Company info
About ServiceNow
ServiceNow provides a cloud-based AI platform that connects people, systems, and processes so organizations can find smarter ways to work. Enterprises and organizations use the platform, along with its AI and automation technologies, to design solutions that transform how they operate.