ML/Research Engineer, Safeguards
$350,000–$500,000 year
Hybrid · San Francisco, California, United States
Job Summary
Develop classifiers to detect misuse and anomalous behavior at scale; build systems to monitor harms that span multiple exchanges and develop new methods to analyze signals across contexts; evaluate and improve safety of agentic products by modeling threats and deploying mitigations for prompt injection; conduct research on automated red-teaming, adversarial robustness, and other testing methods to uncover misuse; requires 4+ years in ML/RE, Python, and experience across the deployment pipeline; strong communication skills to explain complex concepts; role located in San Francisco with a location-based hybrid policy.
Required Qualifications
- Bachelor’s degree or equivalent in a relevant field
- 4+ years of experience in ML engineering, research engineering, or applied research
- Proficiency in Python and experience building ML systems
- Ability to work across the research-to-deployment pipeline
- Strong communication skills
- Experience with language modeling and transformers (preferred)
- Experience building classifiers, anomaly detection systems, or behavioral ML (preferred)
- Experience with adversarial machine learning or red-teaming (preferred)
- Experience with interpretability or probes (preferred)
- Experience with reinforcement learning (preferred)
- Experience with high-performance, large-scale ML systems (preferred)
Additional Requirements
- Visa sponsorship: Anthropic sponsors visas; not guaranteed for every role
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.