SlipstreamJobsFresh Startup & VC-Backed Jobs

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

Snowflake - Menlo Park, CA, United States - In-office - posted 2026-07-22

Apply on the company site

SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.

Snowflake is seeking a Senior/Staff Software Engineer to join the Machine Learning Platform team and help build the next-generation ML and inference infrastructure. The role focuses on enabling customers to run machine learning and deep learning workloads natively on Snowflake, addressing challenges around infrastructure optimization, orchestration, performance, and security. Key responsibilities include defining and owning the ML Platform roadmap in collaboration with senior architects and product managers; building and executing a vision for incorporating advances in machine learning that align with business objectives; ensuring operational excellence and meeting commitments around reliability, availability, and performance; collaborating across ML partner teams to improve development velocity; and supporting team members in delivering high technical quality. The ideal candidate brings 7+ years of experience designing, building, and supporting Internet-scale infrastructure, ML platforms, and ML services. Strong expertise in serving LLMs using inference engines (vLLM, TensorRT-LLM, TEI, SGLang) is essential, along with experience serving fine-tuned LLMs (PEFT, DPO, RL). Familiarity with ML frameworks like SKLearn, XGBoost, PyTorch, TensorFlow, and MLflow is valued. Previous experience building batch and real-time ML serving systems is preferred. The candidate should have a track record of building roadmaps and vision for ML teams, leading technical decision-making with architects and PMs, and understanding Snowflake's core platform architecture to evolve it for state-of-the-art ML and LLM workloads. A BS/MS/PhD in Computer Science or equivalent experience is required.

Similar roles