hudSan Francisco, CABuild high-quality, domain-specific benchmarks and infrastructure to rigorously evaluate frontier AI agents on realistic workflows. Requires strong Python/Docker/Linux skills, experience with evals or benchmarks, and a deep understanding of what makes a benchmark reliable and useful.
Research-oriented Machine Learning Scientist developing multimodal ML models (NLP, Speech, Computer Vision) for lifelike voice agents. Requires published papers in large-scale deep learning and familiarity with SOTA AI.
Conduct original research on LLM evaluation, routing optimization, and model behavior using billions of real-world generations. Design novel benchmarks, run large-scale empirical studies, and develop statistical foundations for intelligent routing. Requires MS/PhD, publication track record, deep stats/ML expertise, and Python/SQL skills.
Research Scientist advancing generative audio models (diffusion/flow matching) for music, focusing on vocal synthesis, post-training alignment (DPO/RLHF), or audio editing. Requires PhD, top publications, and PyTorch expertise to turn research into artist-first Spotify products.
Founding Research Scientist on Anthropic's Life Sciences team, designing and executing wet-lab experiments in molecular biology and biochemistry. Partners with computational biologists and uses Claude AI for hypothesis generation, experimental planning, and rapid iteration to drive AI-accelerated biological discoveries.
As the first dedicated education researcher at Anthropic's Education Labs, design and run mixed-methods studies on AI skill development, build/validate learning measures and instruments, and translate insights into product, curriculum, and model improvements. Requires research background in learning sciences or related fields, strong mixed-methods expertise, Python/LLM technical skills, and comfort with ambiguity.