Staff Software Engineer, ML Hardware, YouTube Discovery

Minimum qualifications:

• 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 (recommender systems, LLMs, computer vision, etc) 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.

Preferred qualifications:

• 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, with the ability to convey complex technical concepts clearly and concisely.

Excellent communication skills, with the ability to convey complex technical concepts clearly and concisely.Excellent communication skills, with the ability to convey complex technical concepts clearly and concisely.Excellent communication skills, with the ability to convey complex technical concepts clearly and concisely.Excellent communication skills, with the ability to convey complex technical concepts clearly and concisely.Excellent communication skills, with the ability to convey complex technical concepts clearly and concisely.Excellent communication skills, with the ability to convey complex technical concepts clearly and concisely.Excellent communication skills, with the ability to convey complex technical concepts clearly and concisely.Excellent communication skills, with the ability to convey complex technical concepts clearly and concisely.

About the job

YouTube's growth is generated by Machine Learning (ML) powered personalized recommendations. Over time, these models are growing larger and it's imperative they be efficiently trained and served using Google's ML hardware Tensor Processing Unit (TPU) Simultaneously, Gemini and Large Language Model offer exciting new model architectures and are developing new advancements in ML hardware development.

In this role, you will be responsible for ensuring YouTube's business-critical recommender models best utilize the available ML hardware. To do this, you will be responsible for managing YouTube's participation in hardware development and evaluation programs. Additionally, you will initiate and drive efforts to adapt YouTube's models to take advantage of new accelerator capabilities, for example by adopting quantized training and inference.

At YouTube, we believe that everyone deserves to have a voice, and that the world is a better place when we listen, share, and build community through our stories. We work together to give everyone the power to share their story, explore what they love, and connect with one another in the process. Working at the intersection of cutting-edge technology and boundless creativity, we move at the speed of culture with a shared goal to show people the world. We explore new ideas, solve real problems, and have fun — and we do it all together.

The US base salary range for this full-time position is $189,000-$284,000 + bonus + equity + benefits. Our salary ranges are determined by role, level, and location. The range displayed on each job posting reflects the minimum and maximum target salaries for the position across all US locations. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific salary range for your preferred location during the hiring process.

Please note that the compensation details listed in US role postings reflect the base salary only, and do not include bonus, equity, or benefits. Learn more about benefits at Google.

Responsibilities

• 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.