Research Engineer, Environment Scaling
Software Development
WFA Digital Insight
The demand for AI and machine learning specialists has skyrocketed, with a 25% increase in 2025 alone. Anthropic's commitment to creating reliable and interpretable AI systems sets them apart. As a Research Engineer, you'll need strong technical skills, project management expertise, and a passion for making AI accessible. Before applying, consider your experience with reinforcement learning, fine-tuning large language models, and data operations.
Job Description
About the Role
The Environment Scaling team at Anthropic aims to improve the intelligence of public models for novel verticals and use cases. As a Research Engineer, you will own the end-to-end process of creating RL environments for new capabilities.Responsibilities
- Improve fine-tuning strategies for adapting models to new domains and tasks
- Manage technical relationships with external data vendors
- Collaborate with domain experts to design data pipelines and evaluations
- Explore novel ways of creating RL environments
- Develop QA frameworks to ensure environment quality
Requirements
- Experience with fine-tuning large language models or domain expertise in a relevant area
- Familiarity with reinforcement learning, reward design, or training data curation
- Strong project management and interpersonal skills
How to Stand Out
- Be prepared to discuss your experience with reinforcement learning and fine-tuning large language models
- Highlight your ability to manage technical vendor relationships and iterate quickly on feedback
- Showcase your project management skills, including experience with data operations and QA frameworks
- Develop a strong understanding of Anthropic's mission and values, and be ready to explain how your work aligns with their goals
- Consider creating a portfolio that demonstrates your ability to design and implement RL environments
This is a remote position listed on WFA Digital, the platform for professionals who work from anywhere. Browse more remote jobs across all categories.