Machine Learning Research Engineer

Responsibilities

• Propose and conduct novel research to achieve results on Sohu that are unviable on GPUs
• Translate core mathematical operations from Transformer-based models into maximally performant instruction sequences for Sohu
• Develop deep architectural knowledge to drive best-in-world software performance on Sohu hardware
• Co-design and finetune emerging model architectures for highest efficiency on Sohu
• Guide the Sohu software stack, performance characterization tools, and runtime abstractions by implementing frontier models in Python and Rust

Requirements

• ML research background with interest in hardware co-design
• Experience with Python, PyTorch, and/or JAX
• Familiarity with transformer model architectures and inference serving stacks (vLLM, SGLang, etc.)
• Experience working in distributed inference or training environments
• Cross-functional experience in diverse software and hardware organizations

Preferred Qualifications

• ML systems research and hardware co-design backgrounds
• Published inference-time compute or efficient ML research
• Experience with Rust
• Familiarity with GPU kernels, CUDA compilation stack, or other hardware accelerators

Benefits

• Full medical, dental, and vision packages with 100% of premium covered
• Housing subsidy of $2,000/month for those living within walking distance of the office
• Daily lunch and dinner in the office
• Relocation support for those moving to Cupertino

About the Company

Etched builds AI chips hard-coded for individual model architectures. Its first product, Sohu, supports transformers with an order of magnitude more throughput and lower latency than a B200. Etched Labs is the organization within Etched whose mission is to democratize generative AI and push the boundaries of what is possible in a post-Sohu world. The team is fully in-person in Cupertino and values deep engineering skills without boundaries between research and engineering.