Reinforcement Learning jobs

About Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

About the Role: 

As a Model Behavior Architect at Anthropic, you'll be at the forefront of shaping AI system behavior to ensure it aligns with human values. Working within the Alignment Finetuning team, you'll combine your expertise in model evaluation, prompt engineering, and ethical judgment and knowledge to help create AI systems that respond with good judgment across diverse scenarios.

Responsibilities:

• Design and implement subtle prompting strategies and data generation pipelines that improve model responses
• Identify and fix edge case behaviors through rigorous testing of your data generation pipelines
• Interact with models to carefully identify where model behavior and judgment can be improved
• Gather internal and external feedback on model behavior to document areas for improvement
• Develop evaluations of language model behaviors across judgment-based domains like honesty, character, and ethics
• Work collaboratively with researchers on related teams like Trust and Safety, Alignment Science, and Applied Finetuning

You May Be a Good Fit If You:

• Have extensive experience with prompt engineering and chaining for language models
• Demonstrate strong skills in evaluating AI system outputs on subtle or fuzzy tasks
• Have a background in philosophy, psychology, data science, or related fields
• Care about AI safety and the ethical implications of both current and future AI behaviors
• Are comfortable using basic Python and running basic scripts
• Have a keen eye for identifying subtle issues in AI outputs
• Understand how LLMs are trained and are familiar with concepts in reinforcement learning
• Have experience finetuning large language models
• Are happy to engage in test-driven development and to carefully analyze data and data pipelines

Strong Candidates May Also Have:

• Formal training in ethics or moral philosophy or moral psychology
• Experience in data science with emphasis on data verification
• Conceptual understanding of language model training and finetuning techniques
• Previous experience developing evaluation frameworks for large language models
• Background in AI safety research or similar fields
• Experience with RLHF, constitutional AI, or other alignment techniques
• Published work related to AI ethics or safety
• Knowledge of model behavior benchmarking

Join us in our mission to ensure advanced AI systems behave reliably and ethically while staying aligned with human values.

The expected salary range for this position is:

Annual Salary:

$280,000 - $425,000 USD

Logistics

Education requirements: We require 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.

Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

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.  Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.

How we're different

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.

Come work with us!

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues.