Compiler Architect

d-Matrix

2 months ago

Santa Clara, CA

Hybrid

Full Time

Senior

0 applicants

View Job Listing

Apply to 100+ jobs

About this role

The Compiler Architect at d-Matrix is responsible for designing and implementing a scalable MLIR-based compiler framework focused on cloud-based AI inference, specifically for large-scale NLP and transformer models. This role includes architecting the end-to-end software pipeline for efficient mapping of AI models to distributed compute environments, optimizing for inference latency and throughput. The Compiler Architect will lead the development of compiler strategies, mentor a team of engineers, and collaborate with cross-functional teams to ensure seamless integration and performance in cloud deployments. A strong background in compiler design, ML inference, and cloud infrastructure is essential for success in this role.

Skills

Qualifications

BS in Computer Science or Electrical EngineeringMS in Computer Science or Electrical EngineeringPhD in Computer Science or Electrical Engineering12+ years of experience in Front End Compiler and systems software developmentDeep experience in designing or leading compiler efforts using MLIR, LLVM, Torch-MLIR, or similar frameworks

About d-Matrix

www.d-matrix.ai

d-Matrix is revolutionizing generative AI with its cutting-edge inference platform, Corsair™, designed for ultra-low latency and high throughput in data centers. The platform integrates memory-compute technology, enabling speeds of 60,000 tokens per second with just 1ms latency for advanced models, making it both efficient and sustainable. With a focus on scalability, d-Matrix's products cater to a wide range of enterprise needs, advancing the accessibility and performance of AI technologies. Additionally, d-Matrix is committed to sustainability, allowing organizations to achieve impressive performance while minimizing energy consumption.