AI Research Engineer – Model Compression, Quantization

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

📋 Description

• Utilize low-bit quantization techniques to minimize model size and inference latency for generative AI models while preserving accuracy and output quality.

• Leverage knowledge distillation to transfer skills from larger teacher models to smaller student models, facilitating multimodal reasoning across text, images, and audio.

• Implement pruning methods to eliminate redundant parameters and attention heads.

• Evaluate trade-offs among model size, latency, memory usage, throughput, and accuracy.

• Investigate and apply mixed-precision quantization and advanced compression techniques.

• Keep abreast of the latest research in model compression for multimodal and generative architectures.

• Construct robust compression pipelines and define performance and fidelity metrics.

• Identify and resolve bottlenecks in production inference.

• Design scalable, low-memory, low-latency AI systems for edge devices such as smartphones.

• Document methodologies, experiments, and outcomes to ensure reproducibility and facilitate collaboration.

• Write technical papers and present findings at conferences like NeurIPS, ICML, ICLR, CVPR, ACL, and AAAI.

⛳️ Requirements

• A degree in Computer Science or a related discipline.

• A PhD in NLP, Machine Learning, or a related field is highly preferred.

• Proven experience in AI R&D with notable publications in A* conferences.

• Proficiency with PyTorch deep learning frameworks or similar alternatives.

• Practical experience with Quantization-Aware Training (QAT) and Post-Training Quantization (PTQ).

• Research and practical experience in knowledge distillation.

• Research and practical experience in model pruning.

• Strong understanding of neural network architectures and training methodologies, including transformers, LLMs, VLMs, backpropagation, optimization, and fine-tuning strategies.

• Familiarity with C++ is advantageous.

• Exceptional English communication skills.

• Candidates must specify the country from which they will work.

🏝️ Benefits

• Opportunity to work remotely from any location worldwide.

• Collaborate with a diverse, global team and leading experts in fintech, AI, and blockchain.

• Engage in cutting-edge projects in digital finance, blockchain, AI, and peer-to-peer technology.

• Chance to author technical papers and present findings at prestigious conferences.

• Opportunities for professional collaboration and research.