Full-Time

Backend Compiler Engineer – New College Grad 2026

NVIDIA

NVIDIA

10,001+ employees

Designs GPUs and AI HPC platforms

Compensation Overview

$108k - $178.3k/yr

+ Equity

Company Historically Provides H1B Sponsorship

Santa Clara, CA, USA

In Person

Category
Software Engineering (1)
Required Skills
C/C++

Get referred to NVIDIA

See people who can refer or advise you

Requirements
  • Recent graduate with a Bachelors or Master's degree in Computer Science or Computer Engineering or equivalent experience.
  • Successful completion of an undergraduate Compiler Design class. Background in LLVM code generation.
  • Strong writing and oral skills, as well as an ability to follow best practices for Software Engineering.
  • You possess strong coding skills with C/C++
Responsibilities
  • Investigate problems or improvement opportunities within the NVIDIA Compiler Back End – consistent with your compiler experience and knowledge.
  • Work with global compiler, hardware and application teams to oversee improvements and problem resolutions
  • Be part of a team that is at the center of deep-learning compiler technology spanning architecture design and support through functional languages
Desired Qualifications
  • You wish to specialize in Compiler Design and Construction and have pursued graduate coursework in these areas.
  • Possess hands-on experience with backend compiler design and code generation.
  • Background in LLVM code generation including instruction scheduling, software pipelining, register allocation, GlobalISel, TableGen, LLVM IR, and Machine IR (MIR)
  • Experience with in any of the following areas is a plus: GPU and parallel architectures; CUDA and/or PTX; Graphics (OpenGL, DX or Vulkan).

NVIDIA designs and manufactures graphics processing units (GPUs) and computing platforms used for gaming, data centers, and artificial intelligence. These products work by using parallel processing to handle complex mathematical calculations much faster than standard computer processors, supported by a software ecosystem that allows developers to build and run AI models. Unlike competitors that may focus solely on hardware, NVIDIA integrates its chips with specialized software and cloud services to create a complete environment for high-performance tasks. The company’s goal is to provide the underlying technology necessary to power advanced computing, from realistic video game graphics to autonomous vehicles and large-scale data analysis.

Company Size

10,001+

Company Stage

IPO

Headquarters

Santa Clara, California

Founded

1993

Get referred to NVIDIA

See people who can refer or advise you

Simplify Jobs

Simplify's Take

What believers are saying

  • Rubin delivers 5x faster inference and 3.5x faster training than Blackwell starting H2 2026.
  • Major hyperscalers Microsoft, AWS, Google Cloud, and CoreWe confirmed Vera Rubin implementation ahead of Q3 2026.
  • Rubin Ultra targets 15 ExaFLOPS FP4 inference with 1.5 PB/s NVLink bandwidth per rack in 2027.

What critics are saying

  • HBM4 scarcity from SK Hynix and Micron forces Rubin production cut to 1.5M units in 2026.
  • Kyber NVL144 rack delayed to 2028 due to TSMC 78-layer PCB yield failure, breaking annual cadence.
  • Rubin Ultra cuts HBM4E stacks to 12-Hi, delivering only 2.66x instead of 4x performance gain.

What makes NVIDIA unique

  • Vera Rubin is a six-chip extreme codesigned AI supercomputer platform, not just a GPU.
  • NVIDIA shifted to annual architecture cadence with Rubin, Ultra, and Feynman releases through 2028.
  • Vera CPU with 88 ARM cores enables per-GPU efficiency and 1/10 Blackwell operational costs.

Help us improve and share your feedback! Did you find this helpful?

Benefits

Company Equity

401(k) Company Match

Growth & Insights and Company News

Headcount

6 month growth

0%

1 year growth

-2%

2 year growth

-3%
Yahoo Finance
Aug 5th, 2026
Tesla vs. Nvidia: Which robotics stock wins as $5T market emerges by 2050?

Morgan Stanley estimates the humanoid robotics market could reach $5 trillion by 2050, with both Nvidia and Tesla pursuing opportunities in the space. Nvidia has developed Isaac GR00T, a universal AI foundation model for humanoid robots, alongside its Halos safety system. The company's Jetson Thor supercomputer is used by Boston Dynamics and Amazon Robotics for AI training and simulation. CEO Jensen Huang stated Nvidia's physical AI revenue has reached a $10 billion annual run rate. He predicts it will become the company's "next $100 billion business" within 10 years. Nvidia currently generates $48.5 billion in free cash flow, demonstrating its ability to invest in growth whilst maintaining profitability. The company is positioning itself as a key infrastructure provider for the robotics industry.

Yahoo Finance
Aug 4th, 2026
SpaceX goes exclusive with Nvidia, plans space-based AI servers as revenue hits $2.6B

SpaceX announced it will exclusively use Nvidia's systems for building AI services, CEO Elon Musk said during the company's first earnings call since going public in June. The company expects to have more than 2 gigawatts of compute capacity by year-end and nearly 10 gigawatts by the end of next year. Musk said SpaceX plans to launch Nvidia's Vera Rubin NVL72 rackscale system both on Earth and in space as part of its Starmind satellite programme, set to begin launching next year. Space-based data centres eliminate the need for purchasing large land areas and reduce cooling requirements. SpaceX reported AI revenues of $2.6 billion, up 213% quarter-over-quarter and 247% year-over-year, driven by cloud service agreements with Google and Anthropic, plus increased Grok and X subscriptions.

LinkedIn
Jun 19th, 2026
LinkedIn

This link will take you to a page that’s not on LinkedIn

Mistral AI
May 28th, 2026
Mistral AI raises $1.9B at $13.2B valuation, led by ASML to advance frontier AI research

Mistral AI has raised €1.7 billion in a Series C funding round at an €11.7 billion post-money valuation. The round was led by semiconductor equipment manufacturer ASML Holding, with participation from existing investors including DST Global, Andreessen Horowitz, Bpifrance, General Catalyst, Index Ventures, Lightspeed and NVIDIA. The Paris-based AI company will use the funding to advance its scientific research and develop custom decentralised frontier AI solutions for complex engineering and industrial problems. ASML CEO Christophe Fouquet said the partnership aims to generate benefits for ASML customers through AI-enabled products and solutions. Mistral AI CEO Arthur Mensch stated the investment will help address engineering challenges in the semiconductor and AI value chain whilst maintaining the company's independence.

Decart
May 18th, 2026
Decart Raises $300M: Tech Leaders Back the Company as Both Customers and Investors | Decart AI

With funding led by Radical Ventures, Decart is building the infrastructure layer for the next generation of low-latency AI systems, through three product lines: DOS, an ultra-optimized inference and training stack that enables agents and reasoning models to run smarter and faster; and the models Lucy, its World Model for Immersive Experiences; and Oasis, its World Model for Physical AI – both powered by DOS. Today, we’re also announcing DOS 2.0, with new versions of Lucy and Oasis launching in the coming weeks.