Reliability Engineer

About Etched

Etched is building AI chips that are hard-coded for individual model architectures. Our first product (Sohu) only supports transformers, but has 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, like real-time video generation models and extremely deep chain-of-thought reasoning.

Reliability Engineer 

We are seeking a skilled and detail-oriented Reliability Engineer to join our team. As a Reliability Engineer at Etched, you will play a critical role in ensuring that all components and systems meet our rigorous reliability standards, essential for our datacenter applications. This position requires a deep understanding of reliability engineering principles, as well as experience working with suppliers, ODMs, and JDMs.

Representative Projects: 

• Lead the development, implementation, and management of reliability standards for all suppliers working with Etched. Ensure that all components and systems meet or exceed the required reliability benchmarks.
• Review and verify reliability reports from suppliers, ensuring accuracy and adherence to Etched's standards. Provide guidance and feedback to suppliers to ensure continuous improvement in reliability performance.
• Collaborate with cross-functional teams to review and recommend component selection criteria based on reliability performance. Ensure that all selected components are capable of meeting the long-term reliability requirements of our datacenter applications.
• Evaluate and approve reliability test plans proposed by external vendors. Ensure that the test methodologies and conditions are sufficient to validate long-term reliability under expected operating conditions.
• Conduct in-depth analysis of reliability data provided by suppliers and vendors. Identify trends, potential issues, and areas for improvement to enhance overall reliability.
• Work closely with ODMs (Original Design Manufacturers) and JDMs (Joint Design Manufacturers) to ensure that all products meet Etched quality and reliability standards. Provide technical guidance and support to maintain maximum operational uptime and long-term reliability.
• Review and establish reliability metrics and standards for silicon components, ensuring they meet the stringent requirements for long-term reliability in data center environments.

You maybe a good fit if you have

• Bachelor's or Master's degree in Reliability Engineering, Electrical Engineering, or a related field.
• 5+ years of experience in reliability engineering, with a focus on datacenter applications preferred.
• Strong understanding of reliability standards, testing methodologies, and data analysis techniques. DFMEA / PFMEA / SPC Engineering analysis experience desired. 
• Experience working with suppliers, ODMs, and JDMs in a high-tech environment.
• Excellent communication skills, with the ability to convey complex technical concepts to diverse stakeholders.
• Proven ability to manage multiple projects and deliver results in a fast-paced environment.

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

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 Cupertino, 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.

Benefits:

• Full medical, dental, and vision packages, with 100% of premium covered, 90% for dependents
• Housing subsidy of $2,000/month for those living within walking distance of the office
• Daily lunch and dinner in our office
• Relocation support for those moving to Cupertino