Senior Staff ML Engineer, AI Safeguards - Moveworks
$201k - $352k • Mountain View, CALIFORNIA, United States • Full-time
Posted 7d ago
Job Location
Mountain View, CALIFORNIA, United States
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
LLM Engineer
About the job
Moveworks is seeking a Senior Staff ML Engineer to focus on AI Safeguards. In this role, you will be responsible for designing, building, and shipping critical safeguards within our agent harness. This includes addressing challenges like prompt injection, multi-turn jailbreaks, toxicity, sensitive topics, and data exposure. You will also develop evaluation frameworks to measure the effectiveness of these safeguards, working closely with our Security team to translate their findings into actionable fixes and robust mitigations. A key part of the role involves selecting, integrating, and fine-tuning detection models, balancing performance, latency, and cost for controls operating in the request path. You will also build configurable safeguard policies to empower customers with control over sensitive topic handling and monitor safeguard behavior in production, addressing any regressions.
Responsibilities
- Design, build, and ship safeguards for prompt injection, jailbreaks, toxicity, and sensitive data exposure.
- Develop evaluations to measure safeguard efficacy using various data sources.
- Collaborate with the Security team to implement fixes and mitigations based on adversarial findings.
- Select, integrate, and fine-tune detection models for commercial and government environments.
- Balance quality, latency, and cost for request-path controls.
- Build configurable safeguard policies for customer control over sensitive topics.
- Monitor safeguard behavior in production and address regressions.
Requirements
- 8+ years of experience building production software.
- 3+ years of applied ML experience (training, evaluating, and deploying models).
- Hands-on experience developing LLM safeguards (e.g., guardrail models, content classifiers, prompt injection/jailbreak detection, safety evals).
- Strong model evaluation fundamentals for agent trajectories and text classification.
- Understanding of LLM safeguard bypass methods (e.g., indirect prompt injection, multi-turn jailbreaks).
- Excellent Python experience.
Benefits
- Base pay of $201,300 - $352,300
- Equity (when applicable)
- Variable/incentive compensation
- Health plans, including flexible spending accounts
- 401(k) Plan with company match
- ESPP
- Matching donations
- Flexible time away plan
- Family leave programs
