✦ Luna Orbit — AI & Machine Learning

Senior/Staff Software Engineer - Machine Learning Platform (Inference)

at Snowflake

📍 US-CA-Menlo Park Unknown Posted March 07, 2026
Type Not Specified
Experience senior
Exp. Years 7+ years
Education Not specified
Category AI & Machine Learning

This role involves leading the development of Snowflake's machine learning platform, focusing on scalable inference and supporting AI workloads, especially large language models.

  • Define and own ML platform roadmap
  • Build scalable ML inference solutions
  • Support large language model deployment
  • Collaborate with cross-functional teams
  • Ensure operational excellence of ML services

Technical scope includes building ML infrastructure with frameworks like PyTorch, TensorFlow, MLflow, and inference engines such as TensorRT, supporting both batch and real-time ML serving systems.

The ideal candidate is a senior machine learning engineer or platform architect with over 7 years of experience in building and supporting ML platforms, especially with large language models and inference engines, demonstrating leadership in AI infrastructure.

7+ years designingbuildingand supporting machine learning platformsExperience with serving LLMs using inference engines like vLLMTensorRT-LLMTEISGLangExperience serving fine-tuned LLMs (PEFTDPORL)Experience with frameworks like SKLearnXGBoostPyTorchTensorFlowMLflowBuilding batch and real-time ML serving systems
Experience with cloud ML platformsKnowledge of ML infrastructureExperience with model optimizationExperience with large-scale deployment
PyTorchTensorFlowMLflowTensorRTvLLMTEISGLang
Machine LearningDeep LearningInference EnginesTensorRTPyTorchTensorFlowMLflowLLMsLarge Language ModelsPEFTDPORLModel ServingML Infrastructure
Machine LearningDeep LearningInference EnginesTensorRTPyTorchTensorFlowMLflowLLMsLarge Language ModelsPEFTDPORLModel ServingML Infrastructure
LeadershipCollaborationTechnical DirectionProblem-solvingInnovationTeam Support
Industry Technology / SaaS
Job Function Lead the development and support of Snowflake's machine learning platform infrastructure for AI and LLM workloads
Machine LearningDeep LearningInference EnginesTensorRTPyTorchTensorFlowMLflowLLMsLarge Language ModelsPEFTDPORLModel ServingML InfrastructureBuilding ML platformsSupporting ML workloads

Less than 7 years of relevant experience, Lack of experience with LLM inference engines, No experience with ML frameworks like PyTorch or TensorFlow

Apply for this Position →

Get matched to jobs like this

Luna finds roles that fit your skills and career goals — no endless scrolling required.

Create a Free Profile