Member of Technical Staff, ML Performance

Odysseyml is seeking a Member of Technical Staff (MTS) focused on ML Performance. This critical role involves optimizing the entire machine learning lifecycle, from model training efficiency to real-time inference speed. You will be responsible for identifying performance bottlenecks within complex deep learning models and implementing cutting-edge solutions. Key responsibilities include profiling model execution paths, applying techniques like quantization and pruning, developing optimized serving infrastructure (e.g., using Triton or ONNX Runtime), and ensuring the scalability of ML pipelines on cloud platforms. The ideal candidate has a strong foundation in both machine learning principles and high-performance computing. You must be proficient in Python and have hands-on experience with performance engineering tools to deliver enterprise-grade, efficient AI solutions.

(تازہ ترین نوکریاں، سلیبس اور ٹیسٹ کی تیاری کی مکمل معلومات)