Teams at Modular

Lead a team building an inference optimization platform for LLMs across GPUs and ASICs. Define technical direction, partner with GTM and engineering to tune customer workloads, create scalable optimization systems, and grow a high-impact performance engineering team.

Profile customer LLM inference workloads end-to-end and apply optimizations across GPU kernels, inference engine, and distributed systems. Build tooling and a repeatable automated optimization platform, partner with GTM and engineering to deploy tuned inference in production, and publish technical insights to shape industry best practices.

The role involves enhancing a graph compiler for ML models, optimizing performance across hardware platforms, and collaborating on core technologies.