Engineering Manager, Model Inference at Abridge

You're a seasoned engineering leader with at least a year of management experience and over five years in engineering, specifically focused on machine learning systems. You have a strong grasp of LLM architectures and inference optimizations. **What makes it worth a look...** Abridge is offering a full-time, hybrid Engineering Manager role in San Francisco with a compensation of $220,000 - $270,000 annually. They are pioneers in generative AI for healthcare, aiming to improve clinical documentation. **You might be a good fit if you...** * Have deep, hands-on experience with ML inference frameworks like PyTorch, TensorFlow, TensorRT, or vLLM. * Possess experience with inference optimizations such as batching, quantization, and kernel fusion. * Are familiar with deploying reliable, distributed, real-time systems at scale. * Have experience with parallelism strategies including tensor and pipeline parallelism.