Inference Intern
Etched · San Jose
Infrastructureonsiteintern
At a glance
Highlights
- Port state-of-the-art models to next-gen AI accelerator architecture.
- Optimize routing, runtime and multi-node inference for max performance.
- Co-design hardware instructions and model ops for inference workloads.
What they offer
- 12-week paid internship
- Generous housing support for those relocating
- Daily lunch and dinner in office
- Direct mentorship from industry leaders and world-class engineers
Ideal candidate
A CS or engineering student fascinated by AI accelerators and low-level performance who loves tackling complex systems and co-designing hardware and models to push inference speed.
Requirements
- Pursuing Bachelor's, Master's, or PhD in computer science, computer engineering, applied mathematics, or related field
- Proficiency in Python and C++
- Understanding of performance-sensitive or complex distributed software systems
- Experience porting applications to non-standard accelerator hardware
- Deep knowledge of transformer model architectures and/or inference serving stacks
- remote policy
- Fully in-person, no remote
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
Posted · Last seen