Software Engineer, Inference

Anthropic is seeking a Software Engineer for their Inference team to build the service that generates outputs from their models in production. This role is crucial in driving efficiency, latency, and reliability. As an engineer on this team, you'll work on improving these metrics by solving complex distributed-systems problems across all layers of the stack.

The ideal candidate should have significant software engineering experience and be results-oriented with a bias towards flexibility and impact. You should be willing to pick up slack even if it goes outside your job description, enjoy pair programming, want to learn more about machine learning research, and care about the societal impacts of your work.

Strong candidates may also have experience with high performance, large-scale distributed systems, Kubernetes, Python, and machine learning. The role involves working on projects such as improving inference request routing, building performance models, implementing new model architectures, analyzing observability data, and optimizing accelerator kernels.

Anthropic offers a competitive compensation package including a salary range of $280,000 to $510,000 USD, equity, and comprehensive benefits. The company has a hybrid work policy, expecting staff to be in one of their offices at least 25% of the time.

If you're passionate about creating reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society, this role at Anthropic could be an excellent opportunity to make a significant impact in the field of AI development and safety.