Elevate your career as a Machine Learning Compiler Optimization Engineer. Focus on enhancing deep learning interfaces and compiler stacks for high-performance inference across platforms.
This position involves defining optimized mappings for large-scale inference workloads and prototyping innovative compilation techniques. Collaborate closely with multifunctional teams to shape and feedback software features that unlock new capabilities in architectures. You will also evaluate and enhance performance metrics critical for effective model deployment.
Key Responsibilities: • Define optimized mappings of inference workloads to systems • Prototype current compilation and runtime techniques • Collaborate with teams on architectural feedback and feature design • Monitor performance metrics to ensure efficiency • Contribute to integration of libraries and tooling
Requirements: • MS or PhD with 5 years of experience • Proficiency in C/C++ and runtime development • Hands-on experience with LLVM or MLIR • Familiarity with TensorFlow and ONNX formats • Strong communication and collaboration skills
Be a key player in advancing compiler technology and deep learning for next-generation systems. #J-18808-Ljbffr