Senior AI Engineer with a focus on production-grade agentic systems, LLM infrastructure, and scalable deployment architectures. I design and ship end-to-end AI platforms — from multi-agent orchestration and real-time streaming to cloud-native deployments and system design — across large enterprise environments.
M.Sc. in Multi-Agent Deep Reinforcement Learning. Currently leading AI engineering at a major corporation, building autonomous systems that operate at scale.
Agentic Workflows Multi-agent orchestration, ReAct patterns, tool-use, state machines, Redis Streams
LLM Infrastructure Fine-tuning, prompt engineering, context management, caching strategies
Streaming Architectures SSE, WebSockets, real-time agent thought streaming, async pipelines
System Design Distributed task queues, event-driven systems, API gateway patterns
Production Deployments Docker, AWS, GCP, CI/CD, containerization, async Python services
Observability Structured logging, tracing, observability tools, LLM eval pipelines
Agent Orchestration
LLM Providers & Interfaces
AI/ML Frameworks
Observability & Analytics
Vector Stores
Backend & Data
-FF4438?style=flat-square&logo=redis&logoColor=white){kind=icon}
Infrastructure & Cloud
Open to conversations about agentic infrastructure, LLMOps, and production AI system design.
