Systems engineer focused on autonomous agents, distributed systems, and production AI infrastructure.

Contributor to Hermes-Agent (NousResearch), working on real-world agent systems and orchestration layers.

I design and operate production systems combining:

• multi-agent architectures
• distributed infrastructure
• real-time data pipelines
• AI-driven automation

Focus areas:

• orchestration of agent fleets
• runtime isolation and deployment
• plugin/tooling ecosystems
• observability and reliability at scale

• hermes-orchestrator
  Control plane for fleets of Hermes agents — lifecycle, isolation, plugins, logs, and upgrades.

• Hermes-Agent contributions
  Co-authored merged PRs with core maintainers.

• docker-nginx-nextcloud
  Production-oriented deployment stack for self-hosted infrastructure.

Built and operated a production system over 6+ years covering:

• distributed backend systems (MySQL cluster, Redis, Kafka, Debezium)
• real-time infrastructure (WebSockets, streaming pipelines, Protobuf)
• multicloud deployments (Oracle Cloud + containerized workloads)
• internal frameworks and automation pipelines

Key work:

• high-concurrency backend using Swoole
• event-driven architecture and streaming pipelines
• AI-driven automation and agent orchestration
• deterministic agent workflows with validation loops

This experience shaped my focus on:

• reliability over demos
• systems under real-world constraints
• production-grade AI integration

• multi-agent orchestration systems
• AI infrastructure for real-world workflows
• low-latency and high-throughput architectures
• scaling autonomous systems in production

• Contributor to Hermes-Agent (NousResearch)
• Co-authored merged PRs with core maintainers
• 6+ years building and operating production systems
• Focus on infrastructure, not prototypes