Staff Software Engineer, ML Hardware, YouTube Discovery
Description For Staff Software Engineer, ML Hardware, YouTube Discovery
YouTube, a part of Google, is seeking a Staff Software Engineer to lead their ML Hardware initiatives for the Discovery team. This role sits at the intersection of YouTube's recommendation systems and Google's cutting-edge ML hardware infrastructure. The position involves ensuring YouTube's business-critical recommender models optimally utilize available ML hardware, particularly the Tensor Processing Unit (TPU).
The role requires deep expertise in both software development and machine learning, with a focus on hardware acceleration and model optimization. You'll be responsible for shaping YouTube's ML hardware strategy, particularly in the context of growing model sizes and emerging technologies like Gemini and Large Language Models. This position offers an opportunity to impact how millions of users experience YouTube through improved recommendation systems.
The ideal candidate will bring 8+ years of software development experience, with specific expertise in ML infrastructure and large-scale ML models. Leadership experience is crucial, as you'll be coordinating with various teams across YouTube and Google. You'll work with state-of-the-art ML hardware and have the opportunity to influence future hardware developments.
This role offers competitive compensation, including a base salary range of $189,000-$284,000, plus bonus, equity, and comprehensive benefits. You'll be joining a company that values diversity, inclusion, and the belief that everyone deserves to have a voice. The position is based in San Bruno, CA, where you'll work with teams dedicated to pushing the boundaries of ML hardware optimization and recommendation systems.
Responsibilities For Staff Software Engineer, ML Hardware, YouTube Discovery
- Develop YouTube Discovery's ML hardware adoption strategy
- Initiate and lead engineering efforts to adapt YouTube's recommender models to perform efficiently on future generations of ML hardware
- Lead YouTube's evaluation of new ML hardware, in collaboration with model developers and Google-wide ML hardware and software experts
Requirements For Staff Software Engineer, ML Hardware, YouTube Discovery
- Bachelor's degree or equivalent practical experience
- 8 years of experience in software development, and with data structures/algorithms
- 5 years of experience with ML infrastructure (e.g., model deployment, model evaluation, optimization, debugging)
- 3 years of experience in developing large-scale ML models utilizing ML hardware accelerators
- 2 years of experience in a technical leadership role
- Experience with post-training quantization, quantized aware training, or quantized training for ML models
- Experience with building efficient and reusable AI infrastructure, compilers, or performance engineering
- Experience with optimizing ML models to efficiently run on ML hardware accelerators
- Excellent communication skills
Benefits For Staff Software Engineer, ML Hardware, YouTube Discovery
- Base salary
- Bonus
- Equity
- Medical Insurance
- Vision Insurance
- Dental Insurance
