Inference Software Engineer

About Etched

Etched is building AI chips that are hard-coded for individual model architectures. Our first product (Sohu) only supports transformers, but has an order of magnitude more throughput and lower latency than a B200. With Etched ASICs, you can build products that would be impossible with GPUs, like real-time video generation models and extremely deep & parallel chain-of-thought reasoning agents.

Job Summary

Etched’s Inference SW team enables optimal mapping of models to Sohu’s dataflow architecture and serving requests across multiple chips, hosts and racks. We are seeking a highly skilled and motivated engineer to join our team as we work towards enabling Mixture-of-Experts (MoE) architectures on Sohu systems. You’ll build SW enabling frontier inference performance to satisfy exponentially growing serving demand.

This role is for a general contributor and will be expected to contribute to all parts of our stack. We also have more specialized needs for this team posted on the site.

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

Scale and enhance Sohu’s runtime, including multi-node inference, intra-node execution, state management, and robust error handling

Optimize routing and communication layers using Sohu’s collectives

Develop tools for performance profiling and debugging, identifying bottlenecks and correctness issues

You may be a good fit if you have

Proficiency in Rust and / or C++

Good familiarity with PyTorch and / or JAX.

Good familiarity with transformers architectures

Ported applications to non-standard or accelerator hardware platforms.

Solid systems knowledge, including Linux internals, accelerator architectures (e.g., GPUs, TPUs), and high-speed interconnects (e.g., NVLink, InfiniBand)

Strong candidates may also have experience with

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 large language model architectures, particularly Mixture-of-Experts (MoE).

Experience analyzing performance traces and logs from distributed systems and ML workloads.

Built applications with extensive SIMD (Single Instruction, Multiple Data) optimizations for performance-critical paths.

Familiar with cluster orchestration tools (e.g., Kubernetes, Slurm) and ML platforms (e.g., Ray, Kubeflow)

Experience designing and implementing CI / CD pipelines for MLOps workflows.

Benefits

Full medical, dental, and vision packages, with generous premium coverage

Housing subsidy of $2,000 / month for those living within walking distance of the office

Daily lunch and dinner in our office

Relocation support for those moving to West San Jose

Compensation Range

$175,000 - $275,000

How we’re different

Etched believes in the Bitter Lesson . We think most of the progress in the AI field has come from using more FLOPs to train and run models, and the best way to get more FLOPs is to build model-specific hardware. Larger and larger training runs encourage companies to consolidate around fewer model architectures, which creates a market for single-model ASICs.

We are a fully in-person team in West San Jose, 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 as needed.