Senior Machine Learning Engineer, Quantized Inference

Location:

Redmond, WA or Santa Clara, CA

Compensation:

$152,000 - $287,500/year

Responsibilities:

• Prototype quantization and sparsity recipes for LLM workloads.
• Design and execute post-training quantization experiments.
• Run evaluations of quantized LLM workloads at scale.
• Develop data analysis tools for debugging.
• Participate in code reviews and contribute to open-source libraries.

Requirements:

• Proficient in Python and PyTorch.
• Experience with quantization and model compression techniques.
• 3+ years in an applied ML role.
• MS/PhD in relevant fields.

Ways to stand out:

• Published work in quantization or training.
• Experience with SFT or RLHF pipelines.
• Familiarity with inference frameworks.