Experience
July 2025 - Present
AI Product Manager
Leading R&D to automate complex enterprise inbound sales calls with voice agents; previously product lead for the voice AI platform.
July 2024 - June 2025
Associate AI Product Manager
Led product execution on platform-wide voice AI initiatives, including conversation flow improvements, prompt engineering, and vendor integrations such as third-party data, text-to-speech models, and speech-to-text models.
May 2023 - July 2024
Data Analyst
Contributed to data strategy and analytics for CNET, a tech media site with 50M monthly visitors. Built pipelines, dashboards, and predictive models for forecasting while supporting ML-driven personalization efforts.
Graduated May 2023
M.S. Data Science & B.A. Mathematics
@ University of Colorado Boulder
Focus in machine learning, big data, NLP, and mathematics with a concentration in statistics.
Projects
Autonomous Coding Orchestration System
Three-layer system that takes a high-level plan and autonomously ships it, handling task execution, multi-model adversarial code review, crash recovery, and session management across 4-5+ hour runs without human intervention.
Deep Research
Customizable research tool that compiles web sources into verified reports. Uses a layered architecture to minimize hallucination—claims are extracted from original sources with full attribution.
View on GitHub
CodeFlow Visualizer
Developer observability tool for AI-assisted coding. Analyzes codebases in real-time, visualizes function relationships, and flags when code drifts from documentation.
View on GitHub
AI Morning Briefing
Automated daily briefing that curates AI news, transcribes podcasts, and summarizes newsletters into a single morning digest at 9:30 AM ET.
View on GitHub
In Progress
Continual Learning Multi-Agent System
Taking the single-agent system to a multitude of coordinated agents that get smarter over time. The system captures what works and what fails across runs and feeds those patterns back into future sessions automatically.
Real-Time Agent Observability Platform
Monitoring infrastructure for concurrent autonomous agent runs. Building the tooling to monitor, trace, and intervene across all runs from a single view.
Agentic Deep Research and Evaluation
Connecting research agents that find emerging patterns and failure modes directly into the evaluation pipeline and core system, so new insights improve the system and how it is evaluated.
Have a Conversation
Feel free to ask about my experience.
Click to start conversation
Try asking:
You can also leave a message
Contact
To reach out with opportunities, to collaborate, or if you have any questions.