LLM Post-Training and Agent Platform
Proxy Loop
A fine-tuned Qwen3-8B agent with a Fast/Slow harness and Temporal-backed durable workflows that act for the user across phone, browser, and email.
Jul 2026 - Present
Archive
A complete project archive spanning distributed AI systems, developer tools, data-intensive applications, and full-stack products.
LLM Post-Training and Agent Platform
A fine-tuned Qwen3-8B agent with a Fast/Slow harness and Temporal-backed durable workflows that act for the user across phone, browser, and email.
Jul 2026 - Present
Distributed AI Systems
A Kubernetes-native Go runtime for crash-resumable LLM workflows with event-sourced recovery, PostgreSQL leases and fencing tokens, and OpenTelemetry observability.
Apr 2026 - Jun 2026
Agent Memory and Evaluation
A Python MCP memory harness for carrying decisions, project facts, and preferences across AI coding sessions while detecting stale context.
Jan 2026 - Mar 2026
Multi-Agent Plugin
An MCP-powered Figma agent that uses a LangGraph supervisor and ReAct tool loops to turn natural-language prompts into FigJam components.
Apr 2025 - May 2025
AI/ML & Edge Computing
A KubeEdge and TensorFlow vegetable-recognition system with Django and MQTT management plus a Kubernetes CI/CD pipeline.
May 2023 - July 2023