Research Engineer, Safeguards Labs

Anthropic•San Francisco, NY

22h•Hybrid

About The Position

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. Safeguards Labs is a new team operating at the intersection of research and engineering, chartered to investigate novel safety methods that protect Claude and the people who use it. We prototype new approaches to safe models, usage safeguards, and production safety — pressure-testing ideas through offline analysis and subsets of traffic before they graduate into production systems run by our partner Safeguards teams. Our work overlaps closely with account abuse, model behavior safeguards, and other safeguard subteams, and we serve as a research arm that can take on ambitious, ambiguous problems and turn them into deployed defenses. We're hiring research engineers to define and execute the Labs research agenda. You'll scope your own projects, run experiments end-to-end, and decide when an idea is ready to hand off to a production team — or when to kill it and move on. The team is small and being built deliberately around a roughly 3:1 mix of researchers to software engineers, so each person has substantial latitude over what they work on and high leverage on the team's direction.

Requirements

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.

Nice To Haves

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.