Li Bearden

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.

Equity rate — a 20% discount for BIPOC-led, BIPOC-serving, and neurodivergent-led organizations. No documentation required. Mention it when you get in touch and I’ll apply it to the quote.

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.