Li Bearden / Consulting
Consulting
Applied evaluation engineering for teams that need to ship
Evaluation work from someone who owned eval and custom-training infrastructure in production for five years.
Voice AI & LLM evaluation · Ex-Deepgram · 5 years production ML
What I do
LLM Evaluation
Eval frameworks that surface the failure modes that matter — not just benchmark scores.
ML Infrastructure
Data pipelines, MLflow/Prefect workflows, and internal tooling built for long-term maintainability.
Voice AI & ASR
Speech pipeline architecture, API integration, and production deployment of voice systems.
AI Training & Workshops
Facilitated training for engineering and product teams — in-person or remote, with reusable materials.
Engagements
Intro callA focused 30 minutes to scope your evaluation or ML needs and check fit.
AI readiness assessmentDiscovery, gap analysis, and a written recommendations report.
WorkshopA live session for engineering and product teams, remote or in person, with the recording and materials to keep.
Monthly retainerAdvisory, code review, and async Q&A on a standing basis.
HourlyScoped work across LLM evaluation, ML infrastructure, and voice AI.
Work together
Best fit for teams shipping models to production who need evaluation they can defend. Remote-first from Chiang Mai, with short in-person sprints — including the EU and UK — available for a few weeks at a time.