Inference Software Engineer

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

About Etched

Etched is building hardware for frontier intelligence. We co-design chips, racks, software, and manufacturing to deliver best-in-class throughput and latency across both prefill and decode workloads. Our first products are heavily focused on inference. Backed by hundreds of millions from top-tier investors and staffed by leading engineers, Etched is redefining the infrastructure layer for the fastest growing industry in history.

Key responsibilities

• Support porting state-of-the-art models to our architecture. Help build programming abstractions and testing capabilities to rapidly iterate on model porting.
• Build, enhance, and scale our runtime, including multi-node inference, intra-node execution, state management, and robust error handling.
• Optimize routing and communication layers using our collectives.
• Utilize performance profiling and debugging tools to identify bottlenecks and correctness issues.

You may be a good fit if you have

• Proficiency in C++ or Rust.
• Understanding of performance-sensitive or complex distributed software systems like Linux internals, accelerator architectures (e.g. GPUs, TPUs), Compilers, or high-speed interconnects (e.g. NVLink, InfiniBand).
• Familiarity with PyTorch or JAX.
• Ported applications to non-standard accelerator hardware or hardware platforms.

Strong candidates may also have experience with (Nice-to-have qualifications)

• Developed low-latency, high-performance applications using both kernel-level and user-space networking stacks.
• Deep understanding of distributed systems concepts, algorithms, and challenges, including consensus protocols, consistency models, and communication patterns.
• Solid grasp of Transformer architectures, particularly Mixture-of-Experts (MoE).
• Built applications with extensive SIMD (Single Instruction, Multiple Data) optimizations for performance-critical paths.

Benefits

• Medical, dental, and vision packages with generous premium coverage
  • $500 per month credit for waiving medical benefits
• Housing subsidy of $2k per month for those living within walking distance of the office
• Relocation support for those moving to San Jose (Santana Row)
• Various wellness benefits covering fitness, mental health, and more
• Daily lunch + dinner in our office
• Unlimited compute budget subject to ROI justification

How we’re different

Etched believes in the Bitter Lesson. We are the first inference-focused frontier AI system, betting early on transformer and transformer-like architectures and on increasing model sizes. Our addressable market is the entirety of inference, unlike many of our competitors.

We are a fully in-person team in San Jose (Santana Row), and greatly value engineering skills. We do not have boundaries between engineering and research, and we expect all of our technical staff to contribute to both and work across disciplines as needed.