Adam Kaniasty — Software Engineer
Software engineering, AI agents and machine learning systems.
Warsaw, Poland
I am a Software Engineer at Google, on the Agent Development Lifecycle team. My work spans AI agents, document retrieval, machine learning pipelines and backend applications.
I work with Python, Java, React TypeScript and cloud infrastructure, including Azure, GCP and Kubernetes. My projects range from knowledge graph-based RAG to reinforcement learning for autoscaling and medical imaging inference.
GitHub · LinkedIn · Experience and CV
Selected projects
- Mi-Crow — Mechanistic Interpretability for LLMs — Python library connecting sparse autoencoder training, activation analysis, concept discovery and language-model steering.
- xLungs — Medical Imaging Inference Application — Java Spring and React application coordinating CT image processing, model inference and radiology reports through RabbitMQ on GPU-powered Kubernetes.
- APPI Marketplace — Knowledge Graph RAG — AI agent platform for technical documents, with knowledge graph-based context retrieval, a FastAPI backend and Azure deployment.
- Reinforcement Learning for Kubernetes Autoscaling — Nokia engineering work on DDQN reinforcement learning, time-series prediction and configurable training pipelines for Kubernetes pod autoscaling.
About Adam
Previously, I built a Java and GraphQL workflow platform at Box, an agentic claims application at Capgemini, and medical imaging applications at MI².AI. As APPI's co-founder and CTO, I developed knowledge graph-based retrieval systems. At Nokia, I worked on reinforcement learning for Kubernetes pod autoscaling and configurable ML training pipelines.
I completed a bachelor's degree in Data Science at Warsaw University of Technology and am pursuing a master's degree in Data Science there. Outside engineering, I train tennis and martial arts.
Research and teaching
I co-developed Mi-Crow with Hubert Kowalski for our engineering thesis and co-authored a 2025 publication on radiomic data transformation for radiologists. Read the publication and related research.
I have given talks on RAG, fine-tuning and embeddings, and mentored AI teams at BEST Hacking League. Talks and mentoring.