Consulting & speaking
Clear thinking for teams building with AI.
I help technical leaders, researchers, and organizations understand what language models can do, where evaluations can fail, and how to build more reliable AI systems.
Start a conversation01
Talks
Accessible, research-grounded talks for technical teams, leadership groups, conferences, and general audiences.
- When AI knows it is being evaluated
- Backdoors and hidden behavior in language models
- How to evaluate autonomous AI agents
- What today’s AI systems can—and cannot—do
02
Training
Hands-on sessions that give teams shared concepts, practical methods, and concrete next steps.
- Designing useful and robust LLM evaluations
- Red-teaming models for hidden failure modes
- Building and benchmarking language-model agents
- AI literacy for technical and non-technical teams
03
Advisory
Focused support for consequential technical and strategic decisions involving language models and agents.
- Evaluation and reliability strategy
- Agent safety and deployment readiness
- Research roadmaps and experiment design
- Independent review of AI claims and results