Senior Staff Machine Learning Engineer (AI Safeguards)

ServiceNow

Mountain View, CA • 18m ago • On-site

Senior

On-site

201,300 - 352,300 USD/yr

  1. Select offer
  2. Add resume
  3. Analyze
  4. Improve
  5. Apply
  6. Auto-send · soon

Match your resume with similar open roles

Upload your resume to automatically match with active openings similar to this role.

PDF up to 10 MB

Your resume is private & secure

Resume Checker & Builder preview

Potential salary for Senior Staff Machine Learning Engineer (AI Safeguards) role

Improve your resume now

$201,300 – $352,300/year

Quick Facts

  • Role: Senior Staff Machine Learning Engineer (AI Safeguards)

  • Focus: Safeguards for LLM agents, safety evaluation, and production monitoring

Description

Design, build, and ship safeguards in the agent harness to mitigate prompt injection, jailbreaks (single and multi-turn), toxicity and sensitive topics, and sensitive data exposure. Build evals to measure safeguard efficacy with both false and true positives using datasets from customer reports, adversarial testing, and production traffic. Partner with Security to convert adversarial findings into eval cases and fixes, including mitigations that hold even when detection misses.

Responsibilities

  • Design and implement AI safeguards in the agent harness for LLM safety risks

  • Develop evaluation harnesses and datasets to measure efficacy and reduce false positives/negatives

  • Collaborate with Security to translate findings into evals, fixes, and stronger mitigations

  • Select, integrate, and fine-tune detection models in a shared stack across environments

  • Balance safeguard quality, latency, and cost for request-path controls

  • Build configurable safeguard policies to let customers decide handling of sensitive topics

  • Monitor safeguard behavior in production and fix regressions

Requirements

  • 8+ years building production software

  • 3+ years of applied ML experience (training, evaluating, deploying) in production systems

  • Hands-on experience developing LLM safeguards (guardrail models, content classifiers, prompt injection/jailbreak detection, safety evals)

  • Strong evaluation fundamentals for agent trajectories and text classification, with emphasis on training/evaluation data quality

  • Working knowledge of common safeguard bypass methods (indirect injection via tools/documents, multi-turn jailbreaks)

  • Excellent Python experience

Benefits

  • Base pay range: $201,300–$352,300, plus equity (when applicable)

  • Variable/incentive compensation (and OTE structure for sales roles)

  • Health plans, flexible spending accounts, 401(k) match, ESPP, matching donations

  • Flexible time away plan and family leave programs

See similar jobs

Explore similar jobs and use your resume score to choose where to apply next

See more

Unlock Full Resume Report