Supercomputing Test Software Engineer (Taiwan)

Job Title

Supercomputing Test Software Engineer (Taiwan)

Role Summary

Join Etched's Supercomputing Testing team to design, implement, and run automated test suites for high-performance inference server hardware and software. The role focuses on ensuring system reliability, diagnosing failures, and collaborating with hardware and software engineers and ODM partners to resolve issues before product delivery.

Experience Level

Mid-level. No specific years of experience provided.

Responsibilities

Deliver, run, and maintain automated tests and tooling that validate system operation, performance, and reliability for inference-focused server products.

• Design, develop, and implement automated supercomputing test suites (Python, Go, Bash) covering boot, root-of-trust, system management, workload deployment, and performance.
• Execute tests on server hardware, monitor system health, and analyze results; produce reports and mitigation plans for failures.
• Investigate and debug hardware and software failures; work with internal and external engineering teams to identify root causes and corrective actions.
• Develop and maintain portable testing infrastructure and automation tools runnable across environments.
• Create and maintain documentation for test plans, cases, and results; support continuous improvement of testing processes.
• Develop stress and fault-injection tests, performance monitoring tools, and pod-level dashboards for large-scale AI accelerator testbeds.

Requirements

Core technical skills and practical testing experience required; optional skills indicated separately.

• Must-have: Proficiency in at least one scripting language (Python, Bash, Go).
• Must-have: Experience with software testing methodologies and tools and with version control (Git).
• Must-have: Strong understanding of operating systems (Linux preferred) and server hardware architectures; experience reading and interpreting hardware logs.
• Must-have: Ability to diagnose complex hardware/software issues and communicate findings clearly to cross-functional teams.
• Nice-to-have: Hardware burn-in or reliability testing, performance benchmarking, hardware diagnostic tools, CI/CD experience, low-level protocols (I2C), and data analysis tools.

Education Requirements

Not specified.

About the Company

Company: Etched

Headquarters: San Jose, CA, United States

Etched develops purpose-built AI inference ASICs and systems optimized for transformer models, aiming to deliver significantly higher performance, lower cost, and lower latency than GPUs. The company focuses on enabling applications like real-time video generation and advanced reasoning agents, and is backed by leading investors and engineers.