Alexey

Python, PyTorch, Transformers, NLP, LLM inference optimization,
Docker, FastAPI, GitHub Actions, semantic search, RAG, quantization

Advanced NLP techniques, LLM inference optimization, RAG systems,
quantization methods (GGUF/AWQ/GPTQ)

LLM Inference Benchmark Toolkit - reproducible optimization lab for comparing
backends and quantization methods. QuantCall - benchmarking tool-call accuracy
across GGUF/AWQ/GPTQ backends.

Collaborations on ML/NLP projects, discussions about LLM inference optimization,
RAG systems, reproducible ML pipelines, and practical MLOps