Firmware Intern

Etched; San Jose (CA); On-site; Full time

Benefits offered by this job

12-week paid internship

Generous housing support

Daily lunch and dinner in the office

Job summary

A tech company specializing in AI hardware is seeking a firmware intern to develop firmware for custom ASICs in San Jose. This 12-week paid internship offers mentorship from industry leaders and housing support. Ideal candidates are progressing towards a degree in Computer Science or a related field, with proficiency in C/C++. Responsibilities include working across the stack and ensuring hardware reliability. Apply even if you don't meet every qualification!

Qualifications

• You must have progress towards a degree in a relevant technical field.
• You should be proficient in C/C++ or Rust programming.
• Strong understanding of data structures and algorithms is essential.
• Solid knowledge of low-level software engineering is required.
• Understanding hardware/software co-design is necessary.
• You need excellent communication and collaboration skills.

Responsibilities

• Develop firmware for custom ASICs for large transformer models.
• Work across the stack from drivers to integration with libraries.
• Focus on hardware reliability and peak performance.
• Collaborate with various teams to bring up new silicon.
• Validate features and support AI applications.

Skills

C/C++ or Rust proficiency

Data structures and algorithms fundamentals

Low-level software engineering understanding

Hardware/software co-design understanding

Excellent communication skills

Education

Progress towards a Bachelor's, Master's, or PhD in Computer Science, Engineering, or related field

Job description

About Etched

Etched is building the world’s first AI inference system purpose-built for transformers - delivering over 10x higher performance and dramatically lower cost and latency than a B200. With Etched ASICs, you can build products that would be impossible with GPUs, like real-time video generation models and extremely deep & parallel chain-of-thought reasoning agents. Backed by hundreds of millions from top-tier investors and staffed by leading engineers, Etched is redefining the infrastructure layer for the fastest growing industry in history.

Job Summary

In our firmware role, you will help develop firmware for custom ASICs designed to run large transformer models efficiently. You’ll work across the stack—from low-level drivers, hardware interfaces, and system initialization code to integration with runtime libraries and model-execution frameworks. Your work will focus on making the hardware operate reliably and at peak performance, enabling high-throughput inference and training workloads. You’ll collaborate with hardware, architecture, and software teams to bring up new silicon, validate features, and support real‑world AI applications.

You may be a good fit if you have

• Progress towards a Bachelor’s, Master’s, or PhD degree in Computer Science, Engineering, or a related technical field.
• Proficiency in C/C++ or Rust.
• Strong fundamentals in data structures and algorithms.
• Strong understanding of low-level software engineering.
• Strong understanding of hardware/software co-design.
• Excellent communication and collaboration skills.

Strong Candidates May Also Have (Nice To Have Qualifications)

• Experience with Linux internals, kernel development, or driver debugging.
• Experience with hardware diagnostics or interpreting hardware logs.
• Exposure to server virtualization or CI/CD pipelines.
• Experience with Rust or embedded development.

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

Program details

• 12-week paid internship (June - August 2026).
• Generous housing support for those relocating.
• Daily lunch and dinner in our office.
• Based at our office in San Jose, CA.
• Direct mentorship from industry leaders and world‑class engineers.
• Opportunity to work on one of the most important problems of our time.

For any questions, contact [e-mail].

How We’re Different

Etched believes in the Bitter Lesson. We think most of the progress in the AI field has come from using more FLOPs to train and run models, and the best way to get more FLOPs is to build model‑specific hardware. Larger and larger training runs encourage companies to consolidate around fewer model architectures, which creates a market for single-model ASICs. We are a fully in‑person team in San Jose (Santana Row), and greatly value engineering skills. We do not have boundaries between engineering and research, and we expect all of our technical staff to contribute to both as needed.