Apply

Ready to go for it?

AI Apply speeds things up—apply directly if you prefer.

FREE ACCESS
5,000–10,000 jobs/day
JobTailor Logo

See all jobs on JobTailor

Search thousands of fresh jobs every day.

Discover
  • Fresh listings
  • Fast filters
  • No subscription required
Create a free account and start exploring right away.
NVIDIA

Senior Software Engineer – AI Inference

NVIDIA

Senior Software Engineer contributing to upstream inference engines like vLLM and SGLang on NVIDIA platforms. Focus on high-throughput, low-latency inference optimization.

Posted 7/16/2026full-timeRemote • California, New York, Texas • 🇺🇸 United StatesSenior💰 $152,000 - $241,500 per yearWebsite

Core Competencies

Role fit
Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and optimizing LLM inference systems, with strong programming skills in Python and C++. Proficient in performance profiling, regression testing, and collaboration across teams to enhance multi-GPU performance and reliability.

Highest-signal resume keywords
LLM Inference/Serving StacksPython ProgrammingC++ ProgrammingCUDA ProgrammingPerformance Profiling

ATS Keywords

Tailor your resume
Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills
Systems EngineeringPerformance InvestigationMulti-GPU InferenceRegression TestingConcurrency Concepts
Tools & Technologies
VLLMSGLang
Certifications & Qualifications
BS in Computer ScienceMS in Computer Engineering
Industry Keywords
Distributed SystemsInference-Runtime Capabilities

Tech Stack

Tools & technologies
Distributed SystemsPython

About the role

Key responsibilities & impact
  • Contribute features, fixes, and optimizations upstream to vLLM/SGLang
  • Implement and optimize inference‑runtime capabilities
  • Profile and improve hot paths across layers
  • Improve multi‑GPU inference performance and reliability
  • Build and maintain performance and correctness regression tests
  • Collaborate with model, platform, and SRE teams

Requirements

What you’ll need
  • 5+ years building production software with solid systems engineering fundamentals
  • Experience with LLM inference/serving stacks (e.g., vLLM, SGLang)
  • Strong programming skills in Python plus C++ and/or CUDA
  • Experience with profiling and performance investigation
  • Familiarity with distributed systems concepts and concurrency
  • BS/MS in Computer Science, Computer Engineering, or related field (or equivalent experience)

Benefits

Comp & perks
  • equity
  • benefits 📊 Check your resume score for this job Improve your chances of getting an interview by checking your resume score before you apply. Check Resume Score