Play a key role in advancing compiler technologies that power next-generation AI systems, bridging machine learning frameworks and cutting-edge hardware.
Overview
Seeking a Principal Compiler Engineer to drive innovation across the compiler stack for high-performance ML systems. This role focuses on optimizing how machine learning models are translated and executed on specialized hardware, enabling state-of-the-art performance at scale.
Key Responsibilities
Compiler Strategy & Leadership
- Lead development of compiler infrastructure, best practices, and process evolution
- Drive innovation in optimization techniques for ML workloads
- Collaborate cross-functionally with engineering, research, and product teams
Engineering & Execution
- Design, build, and deploy compiler features across the full stack
- Optimize mapping of ML models (e.g., PyTorch) to underlying hardware architectures
- Contribute to product development and support technical proposals
Collaboration & Impact
- Partner with domain experts and stakeholders to deliver scalable, high-performance solutions
- Enable seamless integration between ML frameworks and hardware acceleration
Profile
- Strong foundation in compiler theory and design
- Proven experience building and shipping complex software systems
- Familiarity with ML frameworks such as PyTorch or TensorFlow
Preferred Strengths
- Experience with MLIR or modern compiler frameworks
- Understanding of machine learning models and workloads
- Exposure to accelerated computing and dataflow architectures
- Strong interest in performance optimization and debugging
