Software Engineer, Systems ML - GenAI Evals Platform

Meta is seeking a Senior Software Engineer to join their Systems ML team focusing on GenAI Evals Platform. This role is crucial to Meta's ambitious goal of making Llama 4 the leading SoTA model and Meta AI the leading assistant worldwide by 2025.

The position involves building a state-of-the-art platform that enables intuitive authoring and maintenance of complex evaluations for multi-modal, agentic, and reasoning use cases. You'll be responsible for developing reliable, efficient, and automated execution of evaluations at scale over GPU/CPU fleets, while ensuring seamless reporting, analysis, and debugging capabilities.

As a senior engineer on this team, you'll collaborate closely with AI research scientists to accelerate the development of next-generation Generative AI models. The role requires expertise in Python and PyTorch, along with deep understanding of large-scale software applications in the ML Systems domain. You'll be optimizing GPU/CPU utilization, ensuring high engineering quality standards, and contributing to publications and open-source initiatives.

The ideal candidate should have 6+ years of experience with a Bachelor's degree (or equivalent combinations with advanced degrees) in Computer Science or related fields. Direct experience with Generative AI and LLMs is preferred, along with knowledge of GPU, CPU, or AI hardware accelerators. The role offers competitive compensation ranging from $70,670 to $208,000 annually, plus bonus, equity, and comprehensive benefits.

Meta provides an innovative environment at the forefront of AI development, working with cutting-edge technology and a global team of experts. The company's commitment to pushing boundaries in AI, combined with its massive scale and impact, makes this an exceptional opportunity for engineers passionate about advancing the field of artificial intelligence and large language models.

The position is based in Bellevue, WA, and offers the chance to work on technology that will shape the future of AI evaluation and development at one of the world's leading tech companies.