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.
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.
Minimum qualifications:
Preferred qualifications:
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.
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.
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.
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.
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.