Machine Learning Engineer

About Etched

Etched is building the world’s first AI inference system purpose-built for transformers - delivering over 10x higher performance and dramatically lower cost and 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. 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.

Job Summary

As Etched prepares to scale up customer deployments, we are seeking passionate Machine Learning Engineers who specialize in inference systems, performance optimization, and full‑stack ML tooling. In this role, you’ll be a core contributor to the Sohu inference ecosystem. You’ll be working at the intersection of model serving, runtime optimization, tooling, and real‑world deployment.

You’ll collaborate closely with research, software, and hardware teams to turn state‑of‑the‑art transformer architectures into highly optimized, production‑ready inference workflows. Your work will directly enable customers and developers to deploy, profile, and scale inference across next‑generation AI hardware.

This role is hands‑on engineering with deep ML / system involvement, ideal for engineers excited to push the boundaries of inference performance and tooling.

Key responsibilities

• Work with the Etched software team to define and document each layer of the Sohu software stack, from on‑chip transaction execution to multi‑rack workload sharding and management
• Implement and refine model execution strategies (e.g., KV cache optimization, speculative decoding, continuous batching)
• Build tools for profiling, benchmarking, and debugging inference workloads to surface bottlenecks and measure impact
• Define and build quick‑start guides; establish the customer experience from installation to first inference request
• Develop performance harnesses for reference models and publish reproducible metrics
• Contribute to GA acceptance suite used in‑house and at customer sites
• Drive design partner success : work alongside Customer Engineering team to triage field issues and unblock customer site installs and integration

You may be a good fit if you have

Strong candidates may also have experience with

Benefits

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 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 as needed.

#J-18808-Ljbffr