ML Infrastructure Engineer, Interpretability
Description For ML Infrastructure Engineer, Interpretability
Anthropic is seeking an ML Infrastructure Engineer to join their Interpretability team. The role focuses on reverse engineering how trained models work, with the goal of making advanced AI systems safe through mechanistic understanding.
Key responsibilities include:
- Implementing and analyzing research experiments at scale
- Optimizing research workflows for efficiency and reliability
- Building tools and abstractions to support rapid experimentation
- Developing infrastructure to improve model safety across teams
The ideal candidate will have:
- 5-10+ years of software engineering experience
- Proficiency in Python and at least one other programming language
- Strong prioritization and problem-solving skills
- Interest in machine learning research and its applications
- Concern for the societal impacts and ethics of their work
Additional valuable experience includes:
- Designing flexible codebases for quick experimentation
- Optimizing large-scale distributed systems
- Collaborating with researchers and ML engineers
- Experience with language modeling, transformers, GPUs, or PyTorch
This role offers the opportunity to work on cutting-edge AI interpretability research, collaborating across teams to improve the safety and understanding of large language models like Claude. The position is hybrid, requiring 25% in-office time, with locations in San Francisco, Seattle, or New York City.
Anthropic offers competitive compensation including salary, equity, and comprehensive benefits. They value diversity and encourage applicants from all backgrounds to apply, even if they don't meet every qualification.
Responsibilities For ML Infrastructure Engineer, Interpretability
- Implement and analyze research experiments, both quickly in toy scenarios and at scale in large models
- Set up and optimize research workflows to run efficiently and reliably at large scale
- Build tools and abstractions to support rapid pace of research experimentation
- Develop and improve tools and infrastructure to support other teams in using Interpretability's work to improve model safety
Requirements For ML Infrastructure Engineer, Interpretability
- 5-10+ years of experience building software
- Highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with python
- Strong ability to prioritize and direct effort toward the most impactful work
- Comfortable operating with ambiguity and questioning assumptions
- Want to learn more about machine learning research and its applications
- Care about the societal impacts and ethics of your work
Benefits For ML Infrastructure Engineer, Interpretability
- Comprehensive health, dental, and vision insurance
- 401(k) plan with 4% matching
- 22 weeks of paid parental leave
- Unlimited PTO
- Stipends for education, home office improvements, commuting, and wellness
- Fertility benefits via Carrot
- Daily lunches and snacks in office
- Relocation support for those moving to the Bay Area
