Performance Modeling Engineer
EtchedVisit Etched website
Etched is an AI-hardware company building rack-scale frontier inference clusters.
San Jose, United States
Funding history
About Etched
Etched co-designs chips, racks, software, and manufacturing systems for efficient inference of frontier AI models, targeting throughput, latency, cost, and power efficiency across prefill and decode workloads.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will develop performance models and projections across workloads and configurations. You will profile deep-learning workloads, identify microarchitectural bottlenecks, drive hardware and software co-optimization, run regressions against real systems and silicon, and inform next-generation architecture decisions.
Requirements
- Performance modeling and analysis experience
- Understanding of computer architecture and accelerator microarchitecture
- Experience profiling deep-learning workloads on hardware accelerators
- Software engineering fundamentals focused on auditability and maintainability
Responsibilities
- Develop performance models and projections across workloads and configurations
- Profile and analyze deep-learning workloads on hardware
- Identify microarchitectural bottlenecks and optimization opportunities
- Drive hardware and software co-optimization
- Run regressions and validate models against real systems and silicon
- Inform next-generation architectural decisions
Benefits
- Medical, dental, and vision coverage
- $500 per month credit for waiving medical benefits
- $2.5k per month housing subsidy for employees living within walking distance of the office
- Relocation support to San Jose
- Wellness benefits covering fitness and mental health
- Daily lunch and dinner
- Unlimited compute budget subject to ROI justification