ML Engineer (LLM / Python)

Senior/Middle+ ML Engineer for an analytical project. Office/hybrid in Moscow, offline (Air-Gapped) environment, powerful hardware. High pay in cash/crypto.

We are looking for a Senior/Middle+ ML Engineer for an analytical project. Work in the office (Moscow), offline (Air-Gapped). Powerful hardware: Mac Studio 512GB + Ubuntu (NVIDIA RTX PRO 6000 96GB).

• Python, vLLM, Ollama, llama.cpp. • Experience with local deployment of LLM models (Llama-3, Qwen) and working with GGUF / FP8 / AWQ formats. Nice to have: • Experience with fine-tuning (Fine-Tuning, LoRA, QLoRA) and building RAG systems (ChromaDB / Qdrant). • Ability to write parsers (Selenium, Playwright).

Work format: office / hybrid (Moscow). There is a test task, which requires visiting the office. Payment: cash/crypto, above market.

Russia

LoRA

llama.cpp

Llama-3

vLLM

Fine-tuning

RAG

AWQ

Python

GGUF

FP8