Principal Staff Software Engineer, LLM Serving at LinkedIn

Department: EngineeringSeniority in posting: director

Compensation

$207,000 – $340,000/yr

Setup: Hybrid
Location: Mountain View, California
Type: Full-time
Level: staff+
Posted: Sep 17, 2026

Description

LinkedIn is hiring a Principal Staff Software Engineer for its AI Infrastructure LLM Serving team to define and evolve large-scale LLM serving and inference infrastructure. The role leads architecture, performance, reliability, scalability, GPU utilization, and cost improvements across model runtimes, compilers, kernels, distributed systems, and hardware, while contributing to open-source serving frameworks and influencing strategy across ML, infrastructure, product, and research teams. It is a hybrid role with a pay range of $207,000 to $340,000.

Required Skills

LLM serving
Distributed systems
CUDA
Triton
Kernel optimization
Quantization
C++

Additional Information

Minimum Education: Bachelor's degree in Computer Science or a related technical field, or equivalent practical experience
Required Previous Experiences: 10+ years of industry experience in software engineering, distributed systems, infrastructure, machine learning systems, or related technical areas
5+ years of experience in architecture, technical leadership, or senior technical leadership across complex systems or multiple engineering teams
Experience designing, building, and scaling large-scale production ML systems, model serving platforms, AI infrastructure, or distributed systems
Experience building or optimizing GPU-based inference systems, including CUDA, Triton, kernel optimization, runtime optimization, or hardware-aware performance tuning
Hands-on programming experience in C++, Python, Go, Java, or Rust, with experience leading technically complex initiatives across teams or organizations
Preferred Qualifications: Master's or PhD in Computer Science, Machine Learning, Electrical Engineering, or a related technical field, with experience at Principal Staff or equivalent scope
15+ years of software engineering experience, including 7+ years in senior technical leadership roles shaping architecture across multiple teams or organizations
5+ years of hands-on experience building or optimizing large-scale LLM serving, AI inference, GPU infrastructure, or production model deployment platforms
Deep experience with CUDA, Triton, GPU kernel optimization, distributed inference, multi-GPU systems, or hardware-aware performance tuning
Experience with inference optimization techniques such as quantization, mixed precision, batching, caching, memory optimization, and latency or throughput tuning
Experience building large-scale, multi-tenant AI serving platforms and balancing performance, reliability, scalability, GPU utilization, and infrastructure cost
Familiarity with or contributions to serving and runtime frameworks such as vLLM, SGLang, Triton, TensorRT, Ray, XLA, TVM, or similar technologies
Ability to set long-term technical strategy, lead complex cross-organizational initiatives, and influence architecture across ML, infrastructure, research, and product teams

About LinkedIn

LinkedIn | 34,053,841 followers on LinkedIn. Founded in 2003, LinkedIn connects the world's professionals to make them more productive and successful. With more than 1 billion members worldwide, including executives from every Fortune 500 company, LinkedIn is the world's largest professional network. The company has a diversified business model with revenue coming from Talent Solutions, Marketing Solutions, Sales Solutions and Premium Subscriptions products.

View full company profile