RTL Design Engineer

ZipRecruiter; Cupertino (CA); On-site; USD 150,000 - 275,000; Full time

Job summary

An innovative company is seeking an RTL Design Engineer to play a vital role in developing AI chips tailored for specific model architectures. This position offers the chance to work on groundbreaking projects that push the boundaries of technology, including real-time video models and deep reasoning capabilities. You will thrive in a dynamic environment, collaborating with a talented team to ensure the efficiency and correctness of cutting-edge designs. With comprehensive benefits and a supportive culture, this role is perfect for those eager to make a significant impact in the AI hardware space.

Benefits

Full medical, dental, and vision coverage

$2,000/month housing subsidy

Daily lunch and dinner at the office

Relocation support

Qualifications

• 5+ years of experience in RTL development.
• Proficient with standard RTL design and synthesis tools.

Responsibilities

• Develop and implement design verification strategies for ASIC designs.
• Work closely with state-of-the-art architectures for machine learning.

Skills

RTL Development

High-Speed Digital Logic

RTL Design and Synthesis Tools

Writing Test Benches

Eager to Learn AI

Tools

PCIe

Ethernet

HBM Technologies

Python

Job description

About Etched

Etched is building AI chips that are hard-coded for individual model architectures. Our first product (Sohu) only supports transformers but offers an order of magnitude more throughput and lower latency than a B200. With Etched ASICs, you can build products that would be impossible with GPUs, such as real-time video models and extremely deep chain-of-thought reasoning.

RTL Design Engineer

As an RTL Engineer at Etched, you will be crucial in ensuring our AI chips operate correctly and efficiently. Your responsibilities include developing and implementing design verification strategies for both existing and upcoming ASIC designs.

You will work closely with state-of-the-art architectures for machine learning. Prior experience with these architectures is not required; a willingness and ability to learn quickly are essential. You will operate in a fast-paced environment with a high degree of autonomy, contributing significantly to Etched’s success.

Representative projects:

• Implement a block to efficiently compute floating point math operators

• Provide feedback to the uArch team to ensure blocks meet timing and area constraints

You may be a good fit if you:

• Have at least 5 years of experience in RTL development

• Have experience with high-speed digital logic

• Are proficient with standard RTL design and synthesis tools

• Familiar with verification work and writing test benches

• Are eager to learn about transformers and other aspects of modern AI

• Are ready to start quickly

Strong candidates may also have experience with:

• PCIe, Ethernet, or HBM technologies

• Transformer models and machine learning

• Numerical representations and functions

• Programming with Python or other scripting languages

We encourage you to apply even if you do not meet every qualification.

How we’re different:

Etched believes in the Bitter Lesson, emphasizing that most progress in AI comes from using more FLOPs to train and run models. Building model-specific hardware allows for more FLOPs, encouraging companies to focus on fewer model architectures, creating a market for single-model ASICs.

We are a fully in-person team in Cupertino, valuing engineering skills. We integrate engineering and research, expecting all technical staff to contribute to both as needed.

Benefits:

• Full medical, dental, and vision coverage, with 100% of premiums paid by us, and 90% for dependents

• $2,000/month housing subsidy for those living near the office

• Daily lunch and dinner at the office

• Relocation support for moving to Cupertino

Compensation Range: $150K - $275K