Agent Evaluation
Practical methods for testing multi-step agent workflows, tracking regressions, and turning ambiguous behavior into measurable release criteria.
Machine Learning Engineering
Reliable infrastructure for enterprise AI agents.
I am a machine learning engineer and data scientist with 6+ years of experience building applied ML systems. My current public work focuses on evaluation, observability, governance, and reusable infrastructure patterns for production AI agents.
Focus Areas
Observability
Trace schemas, dashboards, and debugging practices that make agent behavior easier to inspect across tools, retrieval systems, and orchestration layers.
Governance
Infrastructure patterns for controlled tool use, policy-aware execution, and accountable deployment of AI agents in enterprise environments.