Search the 5 jobs at CentML

As a Senior Software Engineer for LLM inference, you will write scalable, high-quality code for backend software, perform benchmarking and profiling for GPU applications, and conduct tests on the inference pipeline while collaborating with diverse teams.

As a Senior Software Engineer, you will optimize high-performance GPU kernels for Deep Learning applications by profiling ML/DL workloads, identifying performance bottlenecks, and enhancing system architecture. You’ll also develop tests and benchmarks to validate solutions.

Develop high-performance, power-efficient datacenter solutions for Deep Learning. Optimize GPU kernels, write tests, and benchmarks to evaluate solutions. Communicate with product teams to understand and address performance issues.

Build customer-facing applications, craft performant solutions, participate in code reviews, ensure quality and efficiency, meet customer and business needs.

The Software Engineer will contribute to the design and development of the CentML platform, focusing on scalable systems for large-scale machine learning workloads. Responsibilities include building solutions for ML training and inference on GPU clusters and collaborating with product teams to define use cases and performance benchmarks.