Power Validation Engineer
Etched · San Jose
CHECKED 6H AGO
Infrastructureonsite
At a glance
Highlights
- Own end-to-end power characterization of ASIC and mezzanine card to production.
- Drive silicon, package and system decisions from power and thermal findings.
- Run 72h+ stress workloads to surface reliability risks and throttling behavior.
What they offer
- Medical, dental, and vision packages with generous premium coverage
- $500 per month credit for waiving medical benefits
- $2,500 per month housing subsidy for living within walking distance of office
- Relocation support for moving to San Jose (Santana Row)
- Wellness benefits covering fitness, mental health, and more
- Daily lunch and dinner in office
- Unlimited compute budget subject to ROI justification
Ideal candidate
Hands-on power validation engineer who loves the lab and thrives debugging complex hardware-software interactions. You care about measurement rigor and turning data into clear design decisions for cutting-edge AI hardware.
Requirements
- Bachelor's degree in Electrical Engineering or related field
- Deep understanding of ASIC and system-level power delivery including VRM topology, PDN impedance, decoupling strategy and transient response
- Hands-on bench experience with precision shunts, isolated differential probes, and VNA-based PDN impedance measurement
- Expertise with multi-phase power solutions with high dynamic content and low tolerance, including VR tuning
- Strong oscilloscope and lab instrument fluency for triggering on rare transient events and correlating multi-channel captures
- Track record of finding bugs that only surface under specific workload or environmental conditions in complex hardware-software stack
- Relevant experience with silicon bring-up
- remote policy
- Fully in-person
Lab profile
About Etched
Building specialized AI chips and systems for frontier inference with best-in-class throughput and latency.
What they build
- Sohu AI inference chip
- AI racks and hardware systems
- Inference software stack
Known for
- Full-stack co-design of chips, racks, software and manufacturing
- Best-in-class throughput and latency for prefill and decode
- Inference-optimized architecture
Key facts
- Backed by hundreds of millions from top-tier investors