AI Research Engineer – Model Compression, Quantization

This is a fully remote position, open to applicants in United Arab Emirates (UAE).

📋 Description

• Spearhead advancements in model compression and efficient deployment for cutting-edge multimodal AI systems, including large language models (LLMs) and vision-language models (VLMs).

• Concentrate on minimizing model size and computational expenses while maintaining accuracy.

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

• Develop robust compression workflows, set performance and fidelity benchmarks, and resolve bottlenecks in production inference.

• Provide scalable, low-memory, low-latency AI systems on edge devices (e.g., smartphones) that uphold high fidelity and deliver significant real-world value.

⛳️ Requirements

• A degree in Computer Science or a related discipline.

• Preferably a PhD in NLP, Machine Learning, or a related area, supported by a strong background in AI research and development (with notable publications in A* conferences).

• Proficiency with PyTorch deep learning frameworks or similar platforms.

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

• Research and practical experience in knowledge distillation for converting large models into smaller, efficient variants.

• Research and practical experience in model pruning for transforming large models into smaller, efficient versions.

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

• Familiarity with C++ is an advantage (particularly for implementing low-level quantization kernels or inference optimizations).

🏝️ Benefits

• Flexible work arrangements.

• Opportunities for professional development.