I’m a Staff Software Engineer with 14+ years of experience building and evolving large-scale software systems, infrastructure platforms, developer products, and applied AI systems. My work spans distributed systems, cloud infrastructure, platform engineering, SRE, and agentic AI.

I set technical direction for complex initiatives, define architecture and execution strategy, and stay hands-on through implementation, testing, production rollout, and operations. Recent work includes infrastructure capacity modeling, internal developer platforms, and orchestration systems for AI coding agents.

I also work on technical consulting and startup GTM advisory, helping teams make architecture and platform decisions, prepare products for enterprise adoption, shape technical positioning, and connect engineering capabilities with customer and market needs.

My work centers on AI systems, distributed systems, SRE, and platform engineering. I build LLM applications, coding-agent and multi-agent workflows, and production AI systems with a focus on orchestration, evaluation, tool use, retrieval, and reliability. On the infrastructure side, I work on large-scale systems where scalability, resilience, observability, capacity planning, performance, and operational efficiency matter.

I also focus on technical strategy and architecture, including platform modernization, cloud foundations, developer platforms, automation, and self-service infrastructure. Alongside engineering, I provide technical consulting and GTM advisory, helping teams with architecture, enterprise readiness, solution design, customer discovery, and technical positioning. I also work with engineers on technical leadership, career development, and professional growth, including architecture guidance, skill development, interview preparation, and navigating Staff+ engineering paths.

I’m particularly interested in AI and LLM research, including foundation models, reinforcement learning, agent training environments, evaluation, inference, and model serving. I also follow developments in physical AI, robotics, and world models—systems that learn representations of environments, reason about dynamics, and use those models for planning and interaction.

Beyond the models themselves, I’m interested in the infrastructure and economics behind AI: accelerators, model hosting, inference systems, AI data centers, power and cooling, networking, semiconductor supply chains, and the economics of large-scale compute. I enjoy understanding how advances across hardware, infrastructure, and model architecture shape what becomes technically and economically possible.

• AI Concierge Agent — Automated event discovery, registration, and scheduling using agentic orchestration and browser automation.
• Events Pipeline — Serverless event ingestion and hybrid ranking for real-time discovery.
• DSPy Research — Experiments in declarative LLM workflows, prompt optimization, and pipeline evaluation with DSPy.
• Transformer Labs — Hands-on fine-tuning of transformer models (LoRA, quantization, evaluation frameworks) for NLP tasks.
• Voicematch Labs — Speech/audio analysis toolkit and AI-powered pronunciation platform for language learners, featuring ML models, cloud-native APIs, and interactive feedback.
• Atmos Landing Zones — Secure, automated multi-account AWS/Kubernetes provisioning using Terraform and Helmfile.

(Full details, system design charts, and videos are on my Portfolio page.)