CAD Hardware Engineering Intern
Untether AI is a rapidly growing Toronto startup building a next generation hardware AI accelerator for neural net inference. We're designing integrated circuits that will run neural nets orders of magnitude faster, while using less power. This class of chips will be the standard platform for running image recognition, speech synthesis, text-to-speech, and many other applications in data centers, mobile phones, and self-driving cars within the next 5 years.
As we prepare our next chip design for tape out, our hardware design work is focused on a few primary areas:
Hardware Development Platform Engineering
Continuous Integration (CI) for hardware development
Reproducible build systems for hardware development
Maximize throughput of hardware simulations
e.g. parallelize simulations, profile and optimize simulations
Testbench and RTL code generation
Improve design and verification code quality
Tracing and Observability for the DevEx platform e.g. monitoring and dashboards, simulation debug aids
High reliability hardware development environments
We are looking for self motivated and innately curious candidates. You can expect to be put in charge of an important project that will challenge you to learn, and you will be provided with mentoring and guidance from veteran hardware engineers. Because we're building new systems from the ground up, you'll get to work on new unsolved problems.
We encourage interdisciplinarity and learning, so if you have experience in hardware or software, come talk to us. But don't worry if you think your experience is too narrowly focused, we've got great projects for people with a wide range of interests and specializations.
- Join our CAD Engineering team and come learn about our hardware projects. You can pick your own project from a large number of topics, and we'll work together to set the deliverables for your term with us. In general, expect to work closely with your mentor, participate in code reviews (both as reviewee and reviewer).
- Enable new code quality checks that will run as part of HW continuous integration (CI)
- Develop a mission-critical service that links a task runner service to a resource allocator
- Port a design to a reproducible build system
- Develop a code generation tool for CSRs and UVM RAL
- Develop an ISA coverage model/tool that leverages a fast instruction-set simulator (ISS)
- Develop a flow to flag testbench constraints that are too narrow (over-constrained)
- Build telemetry, metrics services and dashboards to improve operational reliability
- Develop a tool that uses machine learning to cluster/bucket related simulation regression failures
- Develop a hybrid environment for running EDA flows both in the cloud and on-prem
- Develop a GUI for visualizing design/testbench state as a debug aid
- Develop in Python, SystemVerilog, Bash and/or Rust
Some examples of tasks:
- We don't have strict skill requirements, but of course prior experience in the tools and skills we use is a plus:
- Tools and programming languages we use: Cadence, Synopsys (VCS, Verdi, VC Static), SystemVerilog, Python, Jupyter Notebooks, Grafana, git, Verilator
- Topics and skills we are interested in include: CI/CD, platform engineering, DevOps, design verification, formal verification, batch computing, distributed computing, cloud computing, SRE and logic design
- We are open to an internship duration anywhere between 4 months to 12 months and can be flexible with start/end dates.
- Start date May 8th, 2023 and end date August 25th, 2023 (4 months)
- Start date May 8th, 2023 and end date April 29th, 2023 (12 months)
A little bit more about Untether AI
Untether AI has developed a groundbreaking new architecture that brings neural net inference to new levels of performance and efficiency. We’ve already sold our product to smart clients who want to get in at ground zero. We’ve done this while continuing to improve our technology creating ultra-efficient, high performance AI chips that eliminates the data movement bottleneck that costs energy and performance in traditional architectures. We’re a team made up of scientists, engineers and entrepreneurs and have the support of tier one investors. We recently received $125 million in our series B funding round which enables us to expand our customer engagements, enhance our software offering, and build the next generation of industry leading AI inference products. Join us to be part of something big - a chance to create the future of AI.