AnthropicSan Francisco, CABuilds next-generation training environments and evaluations for agentic AI models, blending research in reinforcement learning with robust engineering implementation. Requires strong technical judgment, agency, and experience in ML systems.
The Universes team within Research builds training environments for AI models to perform complex, long-horizon agentic tasks in ultra-realistic settings, teaching models to navigate ambiguity, handle interruptions, maintain context, and exercise judgment.
Research Engineers build next-generation training environments for capable and safe agentic AI. This role blends research and engineering, implementing novel approaches, contributing to research direction, reinforcement learning, environment design, and capability evaluations.
Education requirements: At least a Bachelor's degree in a related field or equivalent experience.
Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
Research Engineer builds and optimizes reinforcement learning infrastructure for advancing AI capabilities like agentic models, tool use, and reasoning. Requires Python proficiency, ML frameworks experience, and ability to blend research with scalable engineering.
This role focuses on advancing how OpenAI builds and understands pretraining data at scale. The individual will treat data quality and curation as core research problems, developing new methods to select, combine, and transform data to improve model capabilities.
OpenAI is seeking a Research Engineer/Research Scientist to advance how the company prepares, curates, synthesizes, and understands multimodal data at scale. This role involves working on research and production problems related to synthesizing multimodal content, improving data pipelines, and building quality filters.
Develops embedding models and retrieval systems to enable frontier AI models to access relevant information dynamically. Requires deep expertise in representation learning, vector retrieval, and transformer LLMs, with experience scaling ML systems.
Develops RLHF and post-training methods for personalized, multimodal AI systems on consumer devices, focusing on reward modeling, preference learning, long-horizon evaluation, and alignment with user values. Requires strong ML research background in RLHF and related areas.