Inference Systems Engineer — High-Performance ML Runtime

The Consensus; San Jose (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical/dental/vision benefits

Housing subsidy

Relocation support

Wellness programs

Free lunch/dinner

Job summary

Etched is building hardware for frontier intelligence and seeks engineers to port state-of-the-art models to our architecture and to build scalable runtimes for multi-node inference. You will optimize communication, state management, and error handling while working with Linux internals and accelerator architectures.

Strong candidates will have experience with C++ or Rust, and familiarity with PyTorch or JAX.

Qualifications

• Proficiency in C++ or Rust.
• Understanding of performance-sensitive or complex distributed software systems.
• Familiarity with PyTorch or JAX.
• Ported applications to non-standard accelerator hardware or hardware platforms.

Responsibilities

• Port models to our architecture and help build testing capabilities for rapid iteration.
• Develop and scale runtime for multi-node inference and state management.
• Optimize routing and communication layers across accelerators.
• Use profiling tools to identify bottlenecks and correctness issues.

Skills

C++

Rust

PyTorch

JAX

Tools

Linux internals

Accelerator architectures

High-speed interconnects

Compilers

Job description

Etched is building hardware for frontier intelligence and seeks engineers to port state-of-the-art models to our architecture and to build scalable runtimes for multi-node inference. You will optimize communication, state management, and error handling while working with Linux internals and accelerator architectures.

Strong candidates will have experience with C++ or Rust, and familiarity with PyTorch or JAX.