Etched
Inference Intern
San Jose · On-site · Internship · Posted Dec 8, 2025
- Education
- Progress toward a Bachelor’s, Master’s, or PhD degree in computer science, computer engineering, applied mathematics, or a related field.
About the job
Contribute to designing and optimizing AI accelerator architectures and software for inference workloads, including model porting, runtime development, and performance optimization.
What you'll do
- Help port models to Etched’s architecture and develop programming abstractions and testing capabilities.
- Assist with runtime development and optimization, including multi-node inference, state management, routing, and communication.
- Profile and debug performance and correctness, and implement high-performance Model Toolkit components.
What they ask for
- Progress toward a Bachelor’s, Master’s, or PhD in computer science, computer engineering, applied mathematics, or a related field.
- Proficiency in Python and C++.
- Understanding of performance-sensitive or complex distributed software systems.
- Experience porting applications to non-standard accelerator hardware or platforms; deep knowledge of transformer architectures and/or inference serving stacks.
Nice to have
- Proficiency in Rust; experience with low-latency networking, distributed systems, SIMD optimization, PyTorch or JAX, or Transformer/MoE architectures.
- Math competition experience (AIME, AMC, etc.).
Tools
Python, C++, Rust, Linux, GPUs, TPUs, NVLink, InfiniBand
AI focus
Develop and optimize AI accelerator architectures and software for inference; port transformer models and co-design hardware instructions with model operations.
Model-written summary · the original posting is authoritative