Senior LLVM Compiler Engineer

Nvidia

Confirmed live yesterday High trust

Remote

Quick summary

Work type: Remote
Location: Remote
Salary: $184,000–$287,500 / yr
Posted: 7 days ago
Freshness: Confirmed live yesterday

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $190k

This role $236k

$134k most similar roles pay here $304k

This role pays more than 88% of similar roles. Most pay $151,000–$228,950 — the shaded band above. At the midpoint, this role pays about $236k versus about $190k for comparable roles.

Based on 240 similar postings.

Employer

About Nvidia

Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing

Nvidia currently has 896 open roles on FindRole.

Listed pay typically runs $184,000–$287,500 across 876 roles with salary data.

Most-posted roles

View all roles at Nvidia

At a glance

TL;DR · Senior LLVM Compiler Engineer

Role Posting Log in to save

Senior LLVM Compiler Engineer joins the Compute Compiler Team to focus on upstream engagement with the LLVM ecosystem and advancing compiler technology through sustained participation in open-source communities. This role involves working directly with LLVM, Clang, and MLIR projects to upstream compiler functionality, refactors, and infrastructure from downstream repositories into the broader community. The engineer will lead design discussions, participate in RFCs, and perform code reviews while refactoring proprietary code to meet upstream quality standards. Key responsibilities include advocating for technical needs through credible engineering arguments and collaborating with internal teams to translate hardware requirements into viable compiler solutions. Candidates must possess expert C++ skills, deep knowledge of compiler internals like IR design and transformations, and experience with open-source development workflows. The role addresses the challenge of balancing proprietary product goals with long-term ecosystem health in compiler infrastructure.

Skills

LLVM Clang MLIR C++ Compiler Internals IR Design Code Generation open‑source development CUDA GPU Architecture Parallel Programming Deep Learning Frameworks Technical Writing

What you'll do

Upstream compiler features, refactors, and infrastructure from NVIDIA's downstream codebases into the LLVM, Clang, and MLIR projects.
Lead design discussions, RFCs, and code reviews within open-source communities to ensure long-term maintainability.
Refactor and decompose proprietary NVIDIA compiler code to meet upstream quality and API standards.
Advocate for NVIDIA’s technical requirements through credible engineering arguments and prototypes in the community.
Identify which downstream capabilities are suitable for upstreaming in collaboration with internal teams.
Translate hardware and software requirements into viable solutions for the LLVM ecosystem.
Shape NVIDIA's long-term open-source strategy by balancing platform goals with ecosystem health.
Act as a technical ambassador to build trust and strengthen partnerships within the compiler community.

What we're looking for

Bachelor’s, Master’s, or PhD in Computer Science, Computer Engineering, or a related field (or equivalent experience).
6+ years of experience with LLVM, Clang, MLIR, or similar compiler infrastructures.
Excellent hands-on C++ programming skills.
Solid understanding of compiler internals including IR design, transformations, analyses, and code generation pipelines.
Experience engaging with open-source development workflows, including design discussions, code reviews, and upstream contribution processes.
Ability to navigate complex technical trade-offs while balancing community expectations with internal product needs.
Strong communication skills for technical writing, design articulation, and cross-organizational collaboration.
Proven track record of upstreaming production code or recognized contributions within the LLVM community.

Save