ANY CITY

December 12, 2024
Svitla Systems Inc. is looking for a Senior ML Engineer for a full-time position (40 hours per week) in Romania. Our client is an innovative technology company focused on creating a decentralized GPU infrastructure designed to run large language models (LLMs). The platform aims to simplify the deployment and management of AI workloads, enabling developers to build and scale their AI applications without the complexities associated with traditional infrastructure management. It provides developers and enterprises with tools to execute large-scale AI jobs without the limitations of traditional cloud infrastructure, focusing on efficiency and affordability. Kluster AI supports AI workloads such as summarization, classification, sentiment analysis, and more, utilizing optimized models for enhanced speed and accuracy. London-based company provides a B2B SaaS platform focused on revenue analytics and forecasting to help businesses optimize their sales and performance strategies.

REQUIREMENTS

• 5+ years of experience working as a Machine Learning Engineer.
• Strong understanding of machine learning principles and operating system fundamentals essential for optimization in distributed environments.
• Proven experience in distributed training or inference systems for large-scale models.
• Hands-on experience with large language models (LLMs).
• Understanding algorithmic improvements to enhance model efficiency and performance.
• Knowledge of Python and hands-on experience with ML frameworks such as PyTorch or TensorFlow.

Nice to have:

• Experience with cloud platforms.
• Experience in building large-scale applications and infrastructure leveraging LLMs.
• Expertise in the quantization of large language models, mainly through algorithmic improvements.

• Design, implement, and optimize distributed training or inference systems for large models.
• Explore and develop quantization techniques for large models to improve performance and reduce resource consumption.
• Build scalable applications and infrastructure leveraging LLMs, ensuring performance, reliability, and maintainability.
• Collaborate with other team members to meet customer’s expectations.