Research Engineer (Code Reinforcement Learning)

Join Anthropic, a leading AI safety and research company, as a Research Engineer in the Code Reinforcement Learning team. In this role, you will advance our models' ability to write, edit, test, debug, and ship real software. You will design RL environments and coding tasks, build reward signals and verifiers, run training experiments, and improve the speed and reliability of our pipelines. This position offers a unique blend of research and engineering, with a focus on cutting-edge AI advancements.

• Contribuer au développement de systèmes permettant aux modèles d'utiliser efficacement les ordinateurs et d'améliorer la génération de code grâce à l'apprentissage par renforcement.
• Concevoir des environnements d'apprentissage par renforcement et des tâches de codage, construire les signaux de récompense et les vérificateurs qui capturent ce que signifie "un bon code".
• Collaborer étroitement avec les équipes d'alignement et de sécurité pour garantir que nos systèmes sont à la fois capables et sûrs.
• Care about code quality, testing, and performance
• Are passionate about the potential impact of AI and are committed to developing safe and beneficial systems
• Are comfortable owning systems end to end and debugging across the stack
• Have strong software-engineering skills and deep Python expertise, including async/concurrent programming
• Can balance research exploration with engineering implementation, and engage rigorously in shaping experimental design and interpreting results
• Experience with reinforcement learning, RLHF, post-training, or LLM finetuning
• Built coding agents, code-execution sandboxes, eval harnesses, verifiers, or developer tooling
• Background in program analysis, testing, verification, compilers, or formal methods
• Experience with PyTorch and large-scale distributed training; performance profiling and optimization of ML systems
• Experience with virtualization and sandboxed code execution environments
• CUDA / GPU or TPU kernel experience and accelerator-performance intuition
• Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience
• Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience
• We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed