Software Engineer, LLM Infrastructure
7 days ago
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 chain-of-thought reasoning.
Software Engineer, LLM Infrastructure
Transformer ASICs, like those built by Etched, dramatically improve time-to-first-token latency. For a large model like Llama-3-70B with 2048 input tokens, the TTFT will be single-digit milliseconds (we will announce performance figures publicly at our launch).
However, single-digit millisecond latency means nothing if the rest of the serving stack takes 100+ ms, and customers actually use it (or adopt the optimizations into their own stack). You will help make both of these happen.
You will work with our software team to build software for continuous batching, and write world-class interactive documentation (like Pytorch's Run in Colab feature) to show customers how it works. You will get this software working on our pre-silicon platform, and port it over to work on the physical chips once they are done being fabbed. You will find creative, new ways to improve this latency - can we speculatively decode the user's inputs? Can we pre-empt sequences if we run out of KV cache space and re-compute them later? Can we cache common pre-fills?
Representative projects:
- Working with emulators like Palladium to develop software for chips while they are being fabricated
- Developing algorithms for balancing prefill and completion tokens when serving LLMs
- Profiling network latency when responding to prompts to help eliminate it in our test environment
- Develop ways for customers to work with our pre-silicon infrastructure and understand how their workloads will run on it.
- Build tools for Jupyter notebooks to connect to emulated and physical Etched systems
You may be a good fit if you:
- Have 3+ years of software engineering experience
- Are good at math, and good at communicating mathematical ideas
- Pick up slack, even if it goes outside your job description
- Are results-oriented, and bias towards shipping products
- Want to learn more about machine learning research
We encourage you to apply even if you do not believe you meet every single qualification.
Strong candidates may also have experience with:
- Palladium emulation
- Real-time audio and video communication
- GPU kernel profiling and low-level programming
- Transformer optimizations, such as FlashAttention
- Ongoing research in machine learning
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 Cupertino, 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.
Benefits:
- Full medical, dental, and vision packages, with 100% of premium covered, 90% for dependents
- 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 Cupertino
-
Software Engineer
2 days ago
Cupertino, California, United States Apple Full timeImagine what you could do here. At Apple, we believe new insights have a way of becoming excellent products, services, and customer experiences very quickly. Bring passion and dedication to your job and there's no telling what you could accomplish. The people here at Apple don't just create products — they create the kind of wonder that's revolutionized...
-
Staff Software Development Engineer
6 days ago
Cupertino, California, United States Apple Full time $250,000 - $400,000 per yearThe Apple Data Platform team powers data analytics, exploration, and feature engineering that fuel Siri, Search, Music, Maps, iCloud and many other beloved products in the Apple ecosystem. Our mission is to provide engineers and data scientists with an innovative, reliable, secure, and user-friendly platform for ingesting, storing, processing, and...
-
Software Engineer
6 days ago
Cupertino, California, United States Apple Full time $150,000 - $200,000 per yearJoin Apple's mission to deliver exceptional customer experiences by developing diagnostic tools that allow our technicians to keep millions of Apple devices running smoothly worldwide. As a Software Engineer on our team, you'll create innovative solutions that empower both customers and technicians to quickly identify and resolve device issues, ensuring...
-
NLP Solutions Software Engineer
6 days ago
Cupertino, California, United States Apple Full time $147,400 - $272,100 per yearDo you love creating elegant solutions to highly complex challenges? Do you intrinsically see the importance in every detail? As part of our Silicon Technologies group, you'll help build AI-driven solutions that solve pressing business challenges. You'll ensure Apple products and services can seamlessly and efficiently handle the tasks that make them beloved...
-
Software Engineer
1 week ago
Cupertino, California, United States Apple Full time $147,400 - $272,100 per yearDo you want to help define the future of delivering Apple software to customers? Join the Insights & Release Technologies team to develop productivity products and release technologies focused on optimizing engineering workflows, so that we can deliver amazing software and experiences to millions of Apple users faster. Our team has a passion for innovation...
-
Cupertino, California, United States Amazon Web Services (AWS) Full timeDescriptionThe Annapurna Labs team at Amazon Web Services (AWS) builds AWS Neuron, the software development kit used to accelerate deep learning and GenAI workloads on Amazon's custom machine learning accelerators, Inferentia and Trainium.The AWS Neuron SDK, developed by the Annapurna Labs team at AWS, is the backbone for accelerating deep learning and GenAI...
-
Staff Software Engineer
5 days ago
Cupertino, California, United States Apple Full time $150,000 - $250,000 per yearWe are looking for a Staff level Software Engineer with experience working with the latest LLM's from OpenAI, Anthropic, Gemini, Mistral, Llama etc. 'and custom fine-tuned models i.e(Defog, Nous research) to help us advance our Manufacturing Systems and Operations. You will move fast prototyping ideas and experimenting with new approaches to solve existing...
-
Cupertino, California, United States Apple Full time $125,000 - $175,000 per yearDo you think Computer Vision and Machine Learning can change the world? Do you think it can transform the way millions of people collect, discover and share the most special moments of their lives? We truly believe it can. We are the System Intelligent and Machine Learning (SIML) group that provides foundational computer vision and machine learning...
-
Cupertino, California, United States Apple Full time $200,000 - $400,000 per yearOur team is seeking adept machine learning scientists and engineers to build cutting-edge AI-driven products at Apple. This role focuses on full-stack ML development, from prototyping to production implementation, working closely with hardware, software, and design teams across the company. You'll be joining a select group of accomplished professionals who...
-
Cupertino, California, United States Amazon Full time $129,300 - $223,600The Annapurna Labs team at Amazon Web Services (AWS) builds AWS Neuron, the software development kit used to accelerate deep learning and GenAI workloads on Amazon's custom machine learning accelerators, Inferentia and Trainium.The AWS Neuron SDK, developed by the Annapurna Labs team at AWS, is the backbone for accelerating deep learning and GenAI workloads...
