I'm an AI Research Engineer working across agentic systems, LLM evaluation, secure inference, and production AI infrastructure.
I enjoy exploring open-ended technical problems and turning early ideas into systems that can be prototyped, evaluated, benchmarked, automated, and deployed.
- Agentic AI, tool-using agents, and agent orchestration
- LLM evaluation, benchmarking, and adversarial testing
- Secure and privacy-preserving inference
- Multi-model and multi-provider AI systems
- RAG, embeddings, and semantic retrieval
- AI workflow automation and observability
- Real-time and distributed AI systems
AI & Research: Agentic AI, LLM evaluation, LLM-as-judge, RAG, embeddings, semantic retrieval, MCP, WebMCP, secure inference, FHE
Languages & Systems: Python, TypeScript, JavaScript, Rust, Node.js, React, C/C++, REST, SSE, WebSocket, gRPC
Infrastructure: Docker, Azure, Linux, CI/CD, GitHub Actions, Azure DevOps, PostgreSQL/pgvector, vLLM, Nginx, WebRTC
My work spans research exploration and production engineering, including agent evaluation, AI security, privacy-preserving inference, real-time systems, automation, and deployed software.
Co-inventor of one granted patent and one filed patent application covering remote ICU monitoring and multimodal interaction systems.