# Performance Engineer, GPU

Hiring organization: [Menlo Ventures Portfolio](https://career.thegoodapps.co/organizations/menlo-ventures-portfolio)

Canonical page: https://career.thegoodapps.co/jobs/fa80d77c-d26d-48e9-b4c1-301ced327aa3

Listed on Menlo Ventures Portfolio's own careers site. Applications go to them directly.

- Employment type: full time
- Location: New York, NY
- Salary: 280000 – 850000 USD per year

## Summary

This role focuses on optimizing GPU performance and systems architecture to power large language models at Anthropic. You'll be responsible for kernel development, distributed systems design, and infrastructure optimization across massive-scale GPU clusters if you have deep experience with GPU programming and a drive to solve complex hardware-software integration challenges.

_Our summary, not Menlo Ventures Portfolio's wording._

## Skills named

CUDA, JAX, PyTorch

## Required

- Deep experience with GPU programming and optimization at scale
- Bachelor's degree or equivalent education and experience
- Ability to work across hardware and software stack layers

## Nice to have

- CUDA kernel development experience
- ML compiler and framework internals knowledge
- Performance engineering and profiling expertise
- Distributed systems and collective communication experience
- Low-precision quantization techniques
- Production-scale training infrastructure experience
- Custom kernel development for quantization formats

Apply on Menlo Ventures Portfolio's site: https://job-boards.greenhouse.io/anthropic/jobs/4926227008
