CareerPlanSign in

Senior and/or Principal Software Engineer- LLM Serving Performance

United States, Multiple Locations, Multiple Locations💼 Full-time🗓 2026-09-15 → 2026-09-26

Core

Develop and optimize GPU kernels and runtime components to improve latency, throughput, and hardware efficiency for state-of-the-art LLM serving systems.

Role type

Senior/Principal IC software engineer (LLM serving performance)

Builds

Production LLM serving systems with optimized GPU kernels and runtime components

Domain

Artificial Intelligence / Large Language Model Inference / GPU Computing

Deliverable

production ML models

Required skills

GPU kernel optimization, C++ programming, Python programming, LLM inference parallelism, low-level architecture expertise, cross-team collaboration, technical ownership, AI-assisted development tool usage

Preferred skills

Expertise in vLLM or SGLang, experience with GPU compilation pipelines, track record of creating reusable platforms, ability to mentor technical leaders

Technologies

C++, Python, vLLM, SGLang

Responsibilities

Profile workloads to identify performance bottlenecks, integrate robust optimizations into production systems, collaborate with model/compiler/hardware teams, contribute to engineering standards and technical reviews

Seniority

Senior/Principal, hands-on IC with mentorship responsibilities

Sourced via microsoft · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.