My work sits at the intersection of advanced machine learning and modern security systems.
I work across deep learning research, enterprise-scale security engineering, and domain-specific AI for high-impact scientific and financial applications.
I specialize in representation learning, generative modeling, and building production-ready AI systems.
My experience spans model training, embedding systems, secure infrastructure, and runtime protection workflows.
I build:
- Multi-turn RAG benchmarking and embedding evaluation systems
- Domain-adapted embeddings for financial analytics
- Zero-knowledge secure tooling and encryption workflows
- Dataset transformation and ML automation pipelines
- Deep learning fine-tuning flows (SFT, domain-specific NLP)
- Vision, sequence, and generative architectures (VAE, GAN, Diffusion, ViT)
In ML research, I focus on:
- Generative modeling
- Neural operators and physics-aligned architectures
- Time-series forecasting and anomaly modeling
- Scientific and biomedical AI
- Cancer detection systems using deep representation learning (current work)
Security is a parallel track: cryptographic protocol implementation, secure backend design, reverse engineering (Windows malware), and DevSecOps-driven runtime protection.