Software Engineer, Systems ML - Model Optimization (PhD) - Meta

Meta is looking for software engineers to play a pivotal role designed to further enhance and elevate our AI inference infrastructure. As a member of our team, you will play a significant role in improving the latency and power consumption of our AI models and in building user facing APIs for our ML engineers. Your expertise will enable us to reach new heights in enabling efficient model inference. The position requires a combination of expertise in machine learning and software engineering.

RESPONSIBILITIES

Software Engineer, Systems ML - Model Optimization (PhD) Responsibilities:

• Fine tune, quantize and deploy ML models on-device across phones, AR and VR devices.
• Optimize models for latency and power consumption.
• Enable efficient inference on GPUs.
• Build tooling to develop and deploy efficient models for inference.
• Partner with teams across meta reality labs to optimize key inference workloads.

MINIMUM QUALIFICATIONS

Minimum Qualifications:

• Currently has or is in the process of obtaining a PhD in the field of Computer Science, Computer Engineering or equivalent. Degree must be completed prior to joining Meta.
• Specialized experience in the following machine learning/deep learning domains: model quantization, compression, on-device inference, GPU inference, PyTorch.
• Currently has, or is in the process of obtaining a Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta.
• Must obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment.

PREFERRED QUALIFICATIONS

Preferred Qualifications:

• Proven record of training, fine tuning, and optimizing models.
• 3+ years of experience on accelerating deep learning models for on-device inference.
• Optimizing machine learning model inference on NVIDIA GPUs.
• Familiarity with on-device inference platforms (ARM, Qualcomm DSP).
• Experience with CUDA/Triton.