Frontier Tech Llm Serving Jobs

Experience building or scaling LLM serving systems, including expertise in distributed inference and performance optimization

You'll partner with Product and other cross-functional leaders across the company to define and drive the long-term vision for how Stripe serves its users.

TL;DR: We are looking for several ML Engineers to train, post-train, and evaluate the LLMs at the core of our platform.

Performance engineering Experience with Triton kernels, TensorRT, quantization, or large-scale model serving.

Our work spans efficient LLM training and inference, parallel and diffusion-based generation, sparsity, scaling laws, and training dynamics.

Responsibilities Build and own end-to-end evaluation suites for LLM capabilities: task specs, grading logic, and the dashboards

Familiarity with LLMs, RAG, AI agents, or evaluation frameworks.

Production experience with LLM-powered or conversational products (chat or voice agents), including evaluation and guardrails.

You will mentor and grow senior engineers, build a culture of technical excellence, and serve as a role model for our high engineering standards.

Familiarity with LLM-powered products, evals, or agentic assistants.

You will serve as a technical anchor for our production environment.