LLM/ML Engineer

LLM/ML Engineer with practical experience in training language models from scratch (1B-10B parameters). Projects under NDA. Contact *****.

Training specialized models from scratch on 1B-10B parameters. Main directions: software development, understanding complex Russian-language texts, and function calling. Projects for clients under NDA. Responsibilities: - Prepare data and build training pipelines. - Conduct experiments with architectures, methods, and training regimes. - Train models from scratch and adapt them for target tasks. - Evaluate model quality, analyze errors, and improve results.

Practical experience in training language models: from data preparation to result evaluation. Experience in similar projects or adaptation of ready models using methods beyond SFT. Proficient Python and PyTorch. Understanding transformer training principles and GPU experience. Nice to have: distributed training, memory and training speed optimization, experience with models for code and tool calling.