Model Serving Engineer

Job Summary

To support the deployment of high-performance AI solutions, the full-time Model Serving Engineer will design, build, and operate inference platforms for serving large machine learning models in a 100% remote environment.

Key Responsibilities

• Design and operate model serving platforms for diverse workloads, including LLMs and recommendation systems
• Optimize inference performance through techniques such as continuous batching and request multiplexing
• Implement multi-tenant routing and capacity management systems to balance latency, throughput, and cost

Required Qualifications

• Bachelor's or Master's degree in Computer Science or a related field
• Six or more years of experience in distributed systems or ML platform engineering
• Strong proficiency in Python and a systems language like Go, Rust, or C++
• Hands-on experience with LLM inference frameworks such as vLLM or TensorRT-LLM
• Deep understanding of GPU architecture and performance engineering