Machine Learning Infrastructure Tech Lead

What this role involves

Reducto is seeking an ML Infrastructure Tech Lead to own the systems for high-performance model training and inference. The role is hands-on (80% building, 20% technical direction) and requires 5+ years of production infrastructure experience with ML systems. This is a fully in-person role at the San Francisco office.

Skills this posting asks for

• python
• kubernetes
• cuda
• triton
• vllm
• sglang
• pytorch
• tensorrt-llm
• ray
• gpu
• distributed training
• distributed inference
• model serving
• systems engineering

Requirements

• 5 years of experience
• Level: senior
• Remote policy: onsite

From the employer’s posting

ABOUT REDUCTO Reducto is the agentic document platform for leading AI teams who demand enterprise performance at scale. We provide a comprehensive toolkit for working with documents the way a human would, combining custom in-house and leading frontier models to power efficient and accurate documen…