Skip to content
AnthropicAnthropicSan Francisco, CA

Research Engineer, Safeguards Labs

Research engineer on the Safeguards Labs team building and evaluating novel safety methods to detect misuse, strengthen model safeguards, and reduce real-world harm from Claude.

350k – 850k
HybridML Engineering

About the role

Key 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.

Minimum qualifications

  • 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.
  • Comfortable scoping your own work and switching between research, engineering, and analysis as a project demands.
  • Working familiarity with how large language models operate — sampling, prompting, training.
  • 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.

Preferred qualifications

  • 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.

Skills

PythonMachine LearningLLMsClassifiersModel EvaluationAdversarial MlRed TeamingInterpretabilityData AnalysisAgentic Workflows

Similar roles

ML Engineering jobs
Thinking Machines Lab

Research Infrastructure Engineer

Thinking Machines LabSan Francisco, CA

Build and operate research infrastructure like evaluation frameworks, RL training systems, and experiment tracking platforms. Partner directly with ML researchers to identify bottlenecks, ensure high adoption of tools, and accelerate research velocity.

350k – 475k
On-siteML Engineering
Anthropic

Research Engineer, Knowledge Team

AnthropicSan Francisco, CA +2

Designs new information architectures for LLMs to interact with external data sources, implements finetuning/RL training, builds evaluation sets, and develops agentic search capabilities. Requires strong Python/ML skills and LLM experience.

350k – 850k
HybridML Engineering
Thinking Machines Lab

Research, Vision Expertise

Thinking Machines LabSan Francisco, CA

Conducts research on visual perception, multimodal learning, and large-scale AI model training. Designs architectures, builds datasets and evaluations, and collaborates on frontier models. Requires ML expertise, Python proficiency, and experimental rigor.

350k – 475k
On-siteML Engineering
Thinking Machines Lab

Research, Pre-Training Data

Thinking Machines LabSan Francisco, CA

Designs and implements methods for sourcing, curating, and analyzing large-scale pre-training datasets for AI models, blending research with production-grade data engineering. Requires Python proficiency, deep learning frameworks, and strong ML fundamentals.

350k – 475k
On-siteML Engineering
Thinking Machines Lab

Research, Post-Training Data

Thinking Machines LabSan Francisco, CA

Conducts post-training research for AI models, designing data collection strategies, developing labeling pipelines, modeling human preferences, and iterating on evaluations to improve model alignment, reasoning, and helpfulness. Requires strong Python skills, ML framework proficiency, and experimental rigor.

350k – 475k
On-siteML Engineering