Software Engineer, Interpretability, USA Anthropic Bay Area, USA, Seattle metro a
2 months ago
About the role:
When you see what modern language models are capable of, do you wonder, "How do these things work? How can we trust them?"
The Interpretability team's mission is to reverse engineer how trained models work. We believe that a mechanistic understanding is the most robust way to make advanced systems safe. We're looking for researchers and engineers to join our efforts.
We're focused on mechanistic interpretability, which aims to discover how neural network parameters map to meaningful algorithms.
Some useful analogies might be to think of us as trying to do "biology" or "neuroscience" of neural networks, or as treating neural networks as binary computer programs we're trying to "reverse engineer".
We recently showed that we could extract millions of meaningful features from Anthropic's production Claude 3.0 Sonnet model, along with an initial demonstration of how we can use these features to change the model's behavior by creating ' Golden Gate Claude '.
Achieving these results required a large engineering effort including optimizing sparse autoencoders (SAEs) across many GPUs, and building tools to visualize millions of features.
Work like this is central to our roadmap of using mechanistic interpretability to improve the safety of LLMs like Claude.
A few places to learn more about our work and team are this introduction to Interpretability from our research lead, Chris Olah ; a discussion of our work on the Hard Fork podcast produced by the New York Times, and this blog post (and accompanying video) sharing more about some of the engineering challenges we'd had to solve to get these results.
We collaborate with teams across Anthropic, such as Alignment Science and Societal Impacts to use our work to make Anthropic's models safer.
Responsibilities:
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
You may be a good fit if you:
Have 3-10+ years of experience building software
Are highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with python
Have a strong ability to prioritize and direct effort toward the most impactful work and are comfortable operating with ambiguity and questioning assumptions.
Care about the societal impacts and ethics of your work
Strong candidates may also have experience with:
Designing a code base so that anyone can quickly code experiments, launch them, and analyze their results without hitting bugs
Optimizing the performance of large-scale distributed systems
Collaborating closely with researchers, ML engineers, or data scientists
Language modeling with transformers
GPUs or Pytorch
Representative Projects:
Building Garcon , a tool that allows researchers to easily access LLMs internals from a jupyter notebook
Setting up and optimizing a pipeline to efficiently collect petabytes of transformer activations and shuffle them.
Profiling and optimizing ML training, including parallelizing to many GPUs
Make launching ML experiments and manipulating+analyzing the results fast and easy
Creating an interactive visualization of attention between tokens in a language model
•
-
Engineering Manager, Model Serving
2 days ago
San Francisco, California, United States Anthropic Full timeAbout AnthropicAnthropic is a leading technology company dedicated to developing reliable, interpretable, and steerable AI systems. Our mission is to create AI that is safe and beneficial for our users and society as a whole. Our team is a rapidly growing group of committed researchers, engineers, policy experts, and business leaders working together to...
-
Senior Infrastructure Software Engineer
6 days ago
San Francisco, California, United States Anthropic Limited Full timePosition Overview:Anthropic Limited is on the lookout for skilled and seasoned Infrastructure Engineers to enhance our efforts in developing, scaling, and maintaining innovative AI systems. This role presents an exciting opportunity to engage with advanced AI technologies and contribute to the evolution of state-of-the-art models, aligning with Anthropic's...
-
Senior Infrastructure Software Engineer
1 day ago
San Francisco, California, United States Anthropic Limited Full timePosition Overview:Anthropic Limited is in search of skilled and seasoned Infrastructure Engineers to enhance our capabilities in developing, scaling, and maintaining innovative AI systems. By becoming part of our Infrastructure division, you will engage with pioneering AI technologies and play a significant role in advancing frontier models, furthering...
-
Senior Infrastructure Software Engineer
1 day ago
San Francisco, California, United States Anthropic Limited Full timePosition Overview:Anthropic Limited is on the lookout for skilled and seasoned Infrastructure Engineers to enhance our efforts in the development, scaling, and upkeep of our advanced AI systems. As part of the Infrastructure team, you will engage with pioneering AI technologies and play a vital role in advancing frontier models, aligning with Anthropic's...
-
Senior Infrastructure Software Engineer
1 day ago
San Francisco, California, United States Anthropic Limited Full timePosition Overview:Anthropic Limited is in search of skilled and seasoned Infrastructure Engineers to enhance our capabilities in developing, scaling, and maintaining advanced AI systems. By becoming a part of our Infrastructure division, you will engage with pioneering AI technologies and play a vital role in advancing frontier models, aligning with...
-
San Francisco, California, United States Anthropic Full timeAbout AnthropicAnthropic is a leading artificial intelligence research organization dedicated to developing safe, interpretable, and steerable AI systems. Our mission is to create AI that benefits society as a whole, and we're committed to advancing the field of AI research through collaborative and innovative approaches.About the RoleWe're seeking an...
-
San Francisco, California, United States Anthropic Limited Full timePosition Overview:Anthropic Limited is in search of skilled and seasoned Infrastructure Engineers to enhance our capabilities in developing, scaling, and maintaining innovative AI systems. By becoming part of our Infrastructure division, you will engage with pioneering AI technologies and play a vital role in advancing frontier models, aligning with...
-
Senior Infrastructure Software Engineer
1 day ago
San Francisco, California, United States Anthropic Limited Full timePosition Overview:Anthropic Limited is on the lookout for skilled and seasoned Infrastructure Engineers to enhance our capabilities in developing, scaling, and maintaining innovative AI systems. As part of our Infrastructure division, you will engage with pioneering AI technologies and play a vital role in advancing our mission to establish safe and...
-
AI Research Scientist
23 hours ago
San Francisco, California, United States Anthropic Limited Full timeAbout Anthropic Limited:Anthropic Limited is a leader in the field of artificial intelligence research, committed to creating safe, ethical, and powerful AI technologies. Our vision is to ensure that advanced AI systems are aligned with human values and interests.Position Overview:We are looking for a Research Scientist / Research Engineer to be part of our...
-
San Francisco, California, United States Anthropic Full timeAbout AnthropicAt Anthropic, our mission is to develop AI systems that are reliable, interpretable, and controllable. We aim for our AI technologies to be safe and advantageous for both our users and society at large. Our rapidly expanding team consists of dedicated researchers, engineers, policy specialists, and business leaders collaborating to create...
-
Product Policy Risk Strategist, Trust
6 days ago
San Francisco, California, United States Anthropic Full timeAbout AnthropicAt Anthropic, our goal is to develop AI systems that are reliable, interpretable, and controllable. We are dedicated to ensuring that AI is safe and advantageous for our users and society at large. Our team comprises a rapidly expanding group of passionate researchers, engineers, policy specialists, and business leaders collaborating to create...
-
AI Research Scientist
6 days ago
San Francisco, California, United States Anthropic Limited Full timeAbout Anthropic Limited:Anthropic Limited is a leader in the field of artificial intelligence research, committed to creating safe, ethical, and impactful AI technologies. Our goal is to ensure that advanced AI systems are developed in alignment with human values.Position Overview:We are looking for a Research Scientist / Research Engineer to be part of our...
-
AI Research Scientist
6 days ago
San Francisco, California, United States Anthropic Limited Full timeAbout Anthropic Limited:Anthropic is a pioneering organization in the field of artificial intelligence, focused on the development of safe, ethical, and impactful AI technologies. Our objective is to ensure that advanced AI systems are aligned with human values and interests.Position Overview:We are in search of a Research Scientist / Research Engineer to...
-
AI Research Scientist
6 days ago
San Francisco, California, United States Anthropic Limited Full timeAbout Anthropic Limited:Anthropic is a leading organization in the field of artificial intelligence research, committed to the development of safe, ethical, and impactful AI technologies. Our primary goal is to ensure that advanced AI systems are aligned with human values and interests.Position Overview:We are in search of a Research Scientist / Research...
-
Lead Revenue Accountant
7 days ago
San Francisco, California, United States Anthropic Full timeAbout AnthropicAnthropic is dedicated to developing trustworthy, interpretable, and controllable AI systems. Our goal is to ensure that AI is safe and advantageous for our users and society at large. Our team comprises a rapidly expanding group of passionate researchers, engineers, policy specialists, and business leaders collaborating to create beneficial...
-
AI Research Scientist
1 day ago
San Francisco, California, United States Anthropic Limited Full timeAt Anthropic Limited, we are pioneers in the field of artificial intelligence research, committed to the creation of safe, ethical, and impactful AI technologies. Our vision is to ensure that advanced AI systems are in harmony with human values. We are in search of a Research Scientist / Research Engineer to become a vital part of our Pretraining team,...
-
Applied Finetuning Research Engineer
6 days ago
San Francisco, California, United States Anthropic Limited Full timeAbout Anthropic Limited:Anthropic Limited is committed to the advancement of trustworthy, comprehensible, and manageable AI technologies aimed at ensuring the safety and benefits of AI for users and society at large.Our growing team comprises passionate researchers, engineers, policy experts, and business professionals working together to create AI systems...
-
Applied Finetuning Research Engineer
6 days ago
San Francisco, California, United States Anthropic Limited Full timeAbout Anthropic Limited:Anthropic Limited is committed to the advancement of trustworthy, transparent, and manageable AI technologies aimed at ensuring the safety and utility of AI for individuals and society as a whole.Our dynamic team comprises passionate researchers, engineers, policy experts, and business professionals working together to create AI...
-
Trust and Safety Product Policy Risk Lead
22 hours ago
San Francisco, California, United States Anthropic Full timeAbout AnthropicAt Anthropic, our goal is to develop AI systems that are dependable, understandable, and controllable. We aim for our AI to be secure and advantageous for both our users and society at large. Our team comprises a rapidly expanding group of dedicated researchers, engineers, policy specialists, and business leaders collaborating to create...
-
Applied Finetuning Research Engineer
6 days ago
San Francisco, California, United States Anthropic Limited Full timeAbout Anthropic Limited:Anthropic Limited is at the forefront of creating AI systems that are reliable, understandable, and controllable, aiming to ensure that artificial intelligence is safe and advantageous for both users and society.Position Overview:As a Research Engineer or Research Scientist focusing on Applied Finetuning, you will be instrumental in...
