Bellevue, Menlo ParkFull TimeEngineering
Remotely
pythonpytorchvllmtensorflowmlflowtensorrt llmxgboostsklearn
Job Description
📋 Description Lead the ML Platform to enable state-of-the-art ML/LLM workloads on Snowflake Define and own roadmaps with architects, PMs, and leaders Ensure reliability, availability, and performance of ML services Collaborate with ML partner teams to improve velocity and capability Mentor teammates to deliver high technical quality 🎯 Requirements 7+ years building ML platforms and internet serving infra Strong track record with ML systems and platforms Experience serving LLMs with inference engines (vLLM, TensorRT-LLM, TEI, SGLang) Experience serving fine-tuned LLMs (PEFT, DPO, RL) Proficiency with SKLearn, XGBoost, PyTorch, TensorFlow; MLflow a plus Experience in batch and real-time ML serving systems
Back to all jobs