ML Applications Engineer 

Etched is building the hardware for superintelligence.

GPUs and TPUs are flexible AI chips that can run many kinds of models: CNNs, RNNs, LSTMs, and more. But today, almost all AI workloads, from ChatGPT to self-driving cars, are done on one model architecture: transformers. Using flexible AI chips for transformers is very inefficient: <5% of the transistors on an H100 are used for matrix multiplication!

Etched is building a single-purpose chip exclusively for transformer inference. We only support transformers, but in exchange our chips have an order of magnitude more throughput and lower latency than an H100. With Etched, you can build products that would be impossible with GPUs, like tree-of-thought agents and ultra-low-latency audio chat bots.

Etched is looking for exceptional ML applications engineers to join our team. Building model-specific silicon unlocks new capabilities (e.g. tree search and super low latency applications) - an ideal candidate for this role will help develop products and work with customers who are developing products that aren’t possible without our hardware.

This role will report to the VP of Software.

Responsibilities:

• Provide input for engineers designing our integrations with current transformer-specific inference libraries, like TensorRT-LLM, TransformerEngine, Hugging Face TGI, and vLLM.
• Help profile and understand where latency comes from in modern LLM serving stacks
• Help customers create products that leverage the unique capabilities of model-specific silicon

Requirements:

• Deeply creative and able to think from first principles
• Good understanding of LLM architecture and how to use them to build applications
• 1 year(s) of work experience at a cloud provider, AI company, or LLM startup
• Experience writing performant real-time code AND proficient in Python
• Breadth of knowledge about current research on large language models

Desired qualifications:

• Experience with semiconductor design and development
• Experience with deep learning frameworks (such as PyTorch, Tensorflow)
• Experience with deep learning runtimes (such as ONNX Runtime, TensorRT,...)
• Experience with at least one of TensorRT, TensorRT-LLM, Transformer Engine, or vLLM
• Experience training, tuning and deploying ML models for CV (ResNet,..), NLP (BERT, GPT), and/or Recommendation Systems (DLRM)

Benefits:

• Competitive salary and equity package
• Full medical, dental, and vision packages, with 100% of premium covered
• Work with world-class people and state-of-the-art AIs everyday

Etched is committed to fair and equitable compensation practices. Compensation is determined based on your qualifications and experience. Compensation packages also include generous equity in Etched.

We are an equal opportunity employer and do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability or other legally protected statuses.