EngineerJobs.io
← Back to all jobs
YouTube

Software Engineer III, ML, TPU Efficiency, YouTube

YouTube
Mountain View, CA $147k - $210k/yr Full time Posted 1d ago
Ai Accelerators Data Pipeline Data Processing Developer Engineering Machine Learning Engineer Machine Learning Engineering Ml Optimization Model Optimization Model Quantization Performance Engineering Real Time Inference Software Development Software Engineer Software Engineering Tpus Xla
Apply Now

Job Description

YouTube is hiring a Software Engineer III to improve the efficiency of the models that power the YouTube algorithm. This role focuses on reducing training and serving costs while increasing fleet utilization through work that spans ML workload profiling, algorithmic efficiency, and co-design between model implementation and TPU compiler aspects.

Work location: Mountain View, CA (onsite)

Compensation: $147,000 - $210,000 USD per year + 15% bonus target + equity + benefits

Responsibilities

  • Profile ML workloads to pinpoint compute and memory bandwidth bottlenecks, then optimize accelerator utilization to improve compute efficiency.
  • Explore, implement, and productionize algorithmic efficiency techniques, including low-precision quantization, knowledge distillation, parameter sharing, and attention optimizations.
  • Optimize auxiliary serving and distributed data pipelines, including data ingestion, feature transformation, embedding lookups, and memory caching to support real-time training and inference.
  • Collaborate with ML model developers and researchers to co-design hardware-friendly model architectures and deploy universal efficiency libraries.

Requirements

  • Bachelor's degree or equivalent practical experience.
  • 2 years of experience programming in C++ or Python.
  • 2 years of experience with software design and architecture.
  • 2 years of experience testing and launching software products.
  • Experience with ML model optimization.
  • Experience with ML frameworks such as TensorFlow, JAX, and PyTorch, or ML compilers (e.g., XLA).

Preferred Qualifications

  • Master's degree or PhD in Computer Science or related technical fields.
  • Experience developing accessible technologies.
  • Experience debugging correctness and performance issues across all levels of the ML software stack.
  • Experience with ML compilers and internals, including writing compiler optimization passes.
  • Familiarity with accelerator hardware architectures (TPUs/GPUs).

Technology Stack

C++, Python, TensorFlow, JAX, PyTorch, XLA, TPUs, GPUs

Interview process: In most instances, this position requires in-person interviews as part of the hiring process.

Similar Jobs