Inference Software Engineer - Distributed Runtime

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 distributed systems engineer deeply familiar with building low latency, high performance systems. You’ll build SW enabling frontier inference performance to satisfy exponentially growing serving demand.

In this role, your core focus will be working across systems and research to realize Mixture of Expert (MoE) architectures on Sohu’s system. You will play a key role in scaling out Sohu’s nascent runtime, including multi-node inference, distributed intra-node execution, state management, and robust error handling. You will develop strategies for efficiently mapping and executing MoE models.

Key responsibilities

• Collaborate across systems and research teams to bring MoE architectures to Sohu’s runtime

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

• Optimize expert routing and communication layers using Sohu’s collectives

• Design and implement scalable MoE execution strategies. Evaluate advanced model parallelism approaches such as expert, tensor, and pipeline parallelism

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

You may be a good fit if you have

• Strong proficiency in Rust and/or C++; familiarity with PyTorch and/or JAX.

• 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).

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

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

• A knack for designing user-facing interfaces and libraries, and enjoy looking for that elusive optimum between performance and usability.

Strong candidates may also have experience with

• Developed low-latency, high-performance applications using both kernel-level and user-space networking stacks.

• Ported applications to non-standard or accelerator hardware platforms.

• Contributed to runtime systems with complex, well-documented interfaces, such as distributed storage systems or machine learning runtimes.

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

• Familiarity 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

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.