Tech Stack

Description

You will build, optimize, and scale machine learning infrastructure for large language models, working closely with cross-functional teams to deliver state-of-the-art AI systems that impact millions of enterprise employees.

Requirements

• 2+ years industry experience in ML or infrastructure
• Experience with deep learning frameworks (PyTorch, Huggingface) or LLM serving frameworks (vLLM, TensorRT-LLM)
• Experience building and scaling end-to-end ML systems
• Proficiency in Python and a performant language like C++ or Go
• Bachelor's degree in CS, CE, Math, or equivalent

Responsibilities

• Design, build and optimize scalable ML infrastructure for training, evaluation, and deployment of LLMs
• Build abstractions to automate steps in ML workflows
• Collaborate with cross-functional teams to build new features
• Drive best practices in ML and data engineering