Software Engineer, Systems ML - Model Optimization (PhD)

Meta is seeking software engineers to enhance our AI inference infrastructure. As a team member, you'll play a crucial role in improving the latency and power consumption of our AI models and building user-facing APIs for ML engineers. This position requires expertise in both machine learning and software engineering.

Responsibilities include:

• Fine-tuning, quantizing, and deploying ML models on-device across phones, AR, and VR devices
• Optimizing models for latency and power consumption
• Enabling efficient inference on GPUs
• Building tooling to develop and deploy efficient models for inference
• Partnering with teams across Meta Reality Labs to optimize key inference workloads

Minimum Qualifications:

• PhD in Computer Science, Computer Engineering, or equivalent (completed or in progress)
• Specialized experience in model quantization, compression, on-device inference, GPU inference, PyTorch
• Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
• Must obtain and maintain work authorization in the country of employment

Preferred Qualifications:

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

Meta offers a competitive compensation package, including benefits, and is committed to providing reasonable accommodations for candidates with disabilities or other needs.