Sr. Machine Learning Engineer, ML Models

Tenstorrent•Toronto, ON

10h•$100,000 - $500,000•Hybrid

About The Position

As a Senior Machine Learning Engineer on the ML Models team at Tenstorrent, you’ll take the lead in bringing up and optimizing cutting edge AI models to run on our custom AI devices. You’ll experiment, optimize, and push boundaries while solving real world problems. If you love the craft of ML and want to work on models that are used in real world applications, you’ll feel right at home. This role is hybrid, based out of Toronto, ON, with the opportunity to be remote on a candidate-by-candidate basis.

Requirements

Python programming
Hands-on experience with PyTorch for developing deep learning models.
Deep understanding of ML model architectures, with the ability to optimize both individual components and overall model performance.
Hands-on experience bringing up state-of-the-art ML models on new hardware platforms.
Strong debugging instincts to investigate performance issues, tune architectures, and boost model accuracy and robustness.
Working knowledge of model optimization techniques, like quantization, flash attention, kernel fusing, and multi-device parallelization.
Eligibility to access U.S. export-controlled technology, subject to U.S. export laws and regulations.

Nice To Haves

Curiosity and a desire to experiment, always seeking to understand how complex systems work and how to make them better.
Comfortable leading a small group of engineers and working closely with cross-functional teams.
A curiosity-driven mindset that stays current with ML research and brings practical insights to real-world engineering challenges.

Responsibilities

Bringing up and optimizing cutting edge AI models to run on custom AI devices.
Experimenting, optimizing, and pushing boundaries while solving real world problems.
Leading a small group of engineers and working closely with cross-functional teams.
Bringing up state-of-the-art ML models on new hardware platforms.
Investigating performance issues, tuning architectures, and boosting model accuracy and robustness.
Staying current with ML research and bringing practical insights to real-world engineering challenges.
Getting real ML models to fly on a custom AI accelerator.
Optimizing ML model performance, from application to silicon level.
Going from research paper to production ready ML deployment.
Working alongside compiler, kernel, and hardware teams to drive new features, performance optimizations, and fixes.