I am an AI/ML Engineer and Systems Architect obsessed with the intersection of reliability engineering and autonomous intelligence. My work focuses on bridging the gap between frontier model research and production-grade system reliability. I specialize in architecting Agentic AI systems that don't just "chat" but act, diagnosing infrastructure, mitigating incidents, and reasoning over complex telemetry data with minimal human-in-the-loop latency. 𝗖𝗼𝗿𝗲 𝗧𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝗙𝗼𝗰𝘂𝘀: 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲𝘀: Designing stateful, multi-agent systems and custom orchestration layers to solve non-deterministic problems in SRE and DevOps. 𝗟𝗟𝗠𝗢𝗽𝘀 & 𝗘𝘃𝗮𝗹𝘀: Engineering rigorous evaluation harnesses and CI/CD pipelines for non-deterministic software, ensuring safety and alignment in enterprise deployments. 𝗠𝗟 𝗦𝘆𝘀𝘁𝗲𝗺 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻: Accelerating inference (vLLM, TGI, quantization) and training (3D parallelism: DP/TP/PP) for open-weights models (Mistral, Gemma, gpt-oss, llama) to achieve cost-effective scale. Currently, I lead the technical strategy for GenAI reliability initiatives, a production-grade multi-agent system. My background spans the full stack of computational hardness from embedded C++ optimization on ARM microcontrollers to distributed training pipelines on AWS/GCP. This "bits to billions" perspective allows me to build AI systems that are not only intelligent but fundamentally performant and secure. Building in public and exploring Model Context Protocol (MCP) for standardizing agent-observability integrations. Researching GNN-based anomaly detection for 3D parallelism in distributed training systems. I share what I learn through technical writing 39+ articles on MLwithDev covering production MLOps, multimodal AI, and security testing of ML systems. My work focuses on the messy realities of production AI: how to make models reliable, how to handle failures gracefully, how to build systems that scale beyond proof-of-concept. I bring the rare ability to understand both cutting-edge AI architectures and the operational realities of serving them at scale exactly what's needed to bridge research and production. 📧 Let's connect if you're working on production AI systems, multi-agent architectures.