Anthropic is hiring a Research Engineer (Senior Staff+) for its Safeguards Labs, a team focused on developing safety methods for the Claude model. The role involves defining and executing research agendas, scoping and running experiments, building prototypes for real‑time safeguards, and contributing to broader research on detecting abusive behavior. Candidates should have a strong track record in research, be proficient in Python, and have familiarity with large language models. The position is hybrid, based in San Francisco or New York, and offers competitive compensation, equity donation matching, generous leave, and flexible hours.
Research Engineer (Senior Staff+), Safeguards Labs en Anthropic
Híbrido - San Francisco, CA; New York City, NY
Más vacantes en AnthropicRequirements
Skills
- Have a track record of independently driving research projects from ambiguous problem statements to concrete results, ideally in AI, ML, security, integrity, or a related technical field.
- Are comfortable scoping your own work and switching between research, engineering, and analysis as a project demands.
- Have working familiarity with how large language models operate — sampling, prompting, training — even if LLMs aren't your primary background.
- Are proficient in Python and comfortable working with large datasets.
- Care about the societal impacts of AI and want your work to directly reduce real-world harm.
- Experience building and training machine learning models, including classifiers for abuse, fraud, integrity, or security applications.
- Knowledge of evaluation methodologies for language models and experience designing evals.
- Experience with agentic environments and evaluating model behavior in them.
- Background in trust and safety, integrity, fraud detection, threat intelligence, or adversarial ML.
- Experience with red teaming, jailbreak research, or interpretability methods like steering vectors.
- A history of taking research prototypes and transferring them into production systems.
Responsibilities
- Lead and contribute to research projects investigating new methods for detecting misuse of Claude, identifying malicious organizations and accounts, strengthening model safeguards, and other safety needs.
- Design and run offline analyses over model usage data to surface abuse patterns, build classifiers and detection systems, and evaluate their effectiveness.
- Develop and iterate on prototypes that could eventually feed signals into the real-time safeguards path, partnering with engineers on tech transfer.
- Contribute to a broader research portfolio investigating methods for detecting abusive behavior in chat-based or agentive workflows, and for training the model to robustly refrain from dangerous responses or behaviors without over-refusing.
- Build evaluations and methodologies for measuring whether safeguards actually work, including in agentic settings.
- Write up findings clearly so they inform decisions across Trust & Safety, research, and product teams.
Technologies
PythonLarge language modelsMachine learningData analysisEvaluation methodologies
Descubre si tu currículum está listo para esta vacante
Mira cómo nuestra IA puede optimizar tu currículum y aumentar tus chances en este puesto.