Anthropic is looking to mitigate the risks associated with building AI systems, specifically the potential for models to interact with private user data. The role aims to design, implement, and audit privacy-preserving techniques to ensure responsible data handling.
Requirements
- Experience working on privacy-preserving machine learning
- Strong coding skills in Python and familiarity with ML frameworks like PyTorch or JAX.
- Deep familiarity with large language models, how they work, and how they are trained
- Have experience working with privacy-preserving techniques (e.g., differential privacy and how it is different from k-anonymity, l-diversity, and t-closeness)
- Have published papers on the topic of privacy-preserving ML at top academic venues
- Prior experience training large language models (e.g., collecting training datasets, pre-training models, post-training models via fine-tuning and RL, running evaluations on trained models)
- Prior experience developing tooling to support privacy-preserving ML (e.g., differential privacy in TF-Privacy or Opacus)
Responsibilities
- Lead our privacy analysis of frontier models, carefully auditing the use of data and ensuring safety throughout the process
- Develop privacy-first training algorithms and techniques
- Develop evaluation and auditing techniques to measure the privacy of training algorithms
- Work with a small, senior team of engineers and researchers to enact a forward-looking privacy policy
- Advocate on behalf of our users to ensure responsible handling of all data
Other
- A track record of shipping products and features inside a fast-moving environment
- Experience supporting fast-paced startup engineering teams
- Demonstrated success in bringing clarity and ownership to ambiguous technical problems
- Proven ability to lead cross-functional security initiatives and navigate complex organizational dynamics
- We require at least a Bachelor's degree in a related field or equivalent experience.
- Currently, we expect all staff to be in one of our offices at least 25% of the time.
- We do sponsor visas!
- We greatly value communication skills.
