Opening. As a Performance Engineer, you'll be responsible for identifying and solving novel systems problems that arise when running machine learning algorithms at scale.
What you'll do
You'll be working on large-scale systems problems, developing systems that optimize throughput and robustness, and collaborating with the team to advance their long-term goals of steerable, trustworthy AI.
- Implement low-latency high-throughput sampling for large language models
- Implement GPU kernels to adapt models to low-precision inference
- Write a custom load-balancing algorithm to optimize serving efficiency
What you need
- Significant software engineering or machine learning experience, particularly at supercomputing scale
- Results-oriented, with a bias towards flexibility and impact
- Strong communication skills
Why this matters
At Anthropic, they believe that the highest-impact AI research will be big science. They're an extremely collaborative group, and they value impact over smaller, more specific puzzles.
