AI Research Engineer – Model Compression, Quantization

This is a fully remote position, open to applicants in Spain.

📋 Description

• Lead the development of innovative techniques for model compression and efficient deployment in advanced multimodal AI systems.

• Emphasize the reduction of model size and computational expenses while maintaining accuracy.

• Utilize and enhance compression methodologies such as quantization, knowledge distillation, and pruning.

• Construct resilient compression pipelines and set performance and fidelity benchmarks.

• Tackle production inference bottlenecks effectively.

• Provide scalable, low-memory, and low-latency AI solutions for edge devices (e.g., smartphones) that uphold high fidelity and real-world applicability.

⛳️ Requirements

• A degree in Computer Science or a related discipline.

• Preferably a PhD in NLP, Machine Learning, or a related area, backed by a strong history in AI research and development, including notable publications in A* conferences.

• Proficiency with PyTorch or similar deep learning frameworks.

• Practical experience in model quantization, encompassing both Quantization-Aware Training (QAT) and Post-Training Quantization (PTQ).

• Research and practical experience in knowledge distillation aimed at compressing large models into smaller, efficient variants.

• Research and practical experience in model pruning for the purpose of reducing large models to smaller, efficient forms.

• Strong grasp of neural network architectures and training methodologies, including transformers (e.g., LLMs, VLMs), backpropagation, optimization, and fine-tuning strategies.

• Familiarity with C++ is advantageous, particularly for implementing low-level quantization kernels or optimization of inference processes.

🏝️ Benefits

• Not specified