[ engineering ]
Inference Intern
Etched- Location
- Not specified
- Work mode
- On-site
- Type
- intern
- Listed
Applications go directly to Etched. Ramai takes no fee for placement and no money for ranking.
[ About this role ]
Inference Architecture Intern at Etched, focusing on designing next-generation AI accelerators for inference workloads. Responsibilities include porting models, enhancing runtime systems, optimizing communication layers, and co-designing hardware instructions and model architecture operations.
Skills and focus areas
- inference
- ai accelerators
- compute architectures
- performance optimization
- model porting
- programming abstractions
- testing capabilities
- runtime systems
- multi-node inference
- intra-node execution
- state management
- error handling
Summary written by Ramai from the original posting. Full details and requirements are on Etched’s careers page.
[ More at Etched ]
See all 123 open roles at Etched →[ Similar roles at other startups ]
- Senior Software EngineerVariance
- Fullstack Software EngineerSirdab
- Member of Technical Staff, Typescript Engineer (principal)Inkeep
- Founding Full Stack Engineer - Llm, Applied Ai (no Prior Llm Experience Required)Berry
- Engineers That Enjoy Hard Things (like Compilers)Boundary
- Forward Deployed EngineerVooma
[ Not quite right? ]
Tell the assistant what you’re after — stage, location, stack, visa sponsorship — and it searches every open role for you. A few questions are free, no account needed.