Senior software
engineer at the seams.
I build internal platforms, AI agent systems, and ML workflows that teams use in production. Currently shipping at Aspen Power Partners.
What I do.
Four things I'm asked to build, again and again.
- 01
AI agent platforms
Production multi-agent systems with human approval boundaries, governed write paths, and isolated runtime containers.
- 02
Full-stack SaaS
Systems where the data model, API, and interface are designed together, so users get fast workflows instead of stitched-together screens.
- 03
ML and forecasting
Multi-model tournaments across deep-learning and gradient-boosted baselines, custom domain metrics, and rigorous data-leakage discipline.
- 04
Reverse engineering
Static and dynamic analysis with Ghidra, ILSpy, and Frida. From-scratch protocol reimplementations when the official SDK does not work.
Selected systems.
AMOS
→ ReadAsset Management Operations System. AMOS is the operations hub Aspen’s asset team uses every day to run a fleet of solar sites from one place.
AgentOS
→ ReadEnterprise Multi-Agent Platform. AgentOS is a control plane for running AI agents inside a company: roles, teams, approvals, channels, memory, and runtime isolation managed from one dashboard.
AIVA
→ ReadDocument Intelligence Platform. AIVA is a document-intelligence platform for internal company documents: HR, contracts, financials, and asset records.
Forecasting and Failure Prediction
→ ReadIn-house ML platform. A 16-day solar power forecasting platform that compares deep-learning models against gradient-boosted baselines.
I'm strongest at the seams. The boundary between a frontend and a backend, a service and a database, an AI agent and a human approver.