At Innowise, I work as an ML Engineer / AI Engineer, developing AI services with experience in NLP, LLMs, and agentic systems.
I work with RAG, vector search, embeddings, and BERT, and fine-tune LLMs using PEFT, LoRA, and QLoRA.
My work includes LLM evaluation, including offline and online evaluation and LLM-as-a-Judge, as well as agentic workflows with LangGraph and function calling.
I also have experience deploying AI services on GPU and CPU using Docker, Kubernetes, and CI/CD, and monitoring them with Prometheus and Grafana.
