5+ years building production voice AI, ML infrastructure, and evaluation frameworks. Based in Thailand — working globally.
Production-grade AI engineering for startups, enterprises, and organizations making an impact.
API integration, speech pipeline architecture, and production deployment of voice AI systems.
Eval framework design, fine-tuning strategy, and quality benchmarking for production LLMs.
Data pipelines, MLflow/Prefect workflows, and internal tooling for ML teams.
In-person and remote facilitated training programs. Materials development for unlimited internal reuse.
Tech writing, API documentation, blog posts, and developer advocacy programs.
Facilitated in-person session, prep, and materials included.
Live remote session plus evergreen recording kit for ongoing training.
Both in-person session and evergreen remote kit. Travel costs additional.
Discovery sessions, gap analysis, and a written recommendations report.
Up to 20 hrs/month — advisory, code review, and async Q&A.
I'm Elliot "Li" Bearden, an Applied AI Engineer with 5+ years building production systems at Deepgram, a voice AI unicorn. I started in customer support and worked my way up through data pipeline engineering, model evaluation, and custom training programs—supporting 150+ enterprise customers and contributing to a $72M Series B.
Today I consult independently, helping startups and mission-driven organizations design and ship AI systems that work in the real world—not just in demos. I specialize in the gap between "the API works" and "this is in production."
Outside of code, I'm a conservation enthusiast and outdoorsman. I build tools to connect underserved communities with the natural world, blending technology with a commitment to sustainability and inclusion.
Ready to build something? Let's talk about your project.
Whether you need a one-day AI readiness assessment, an ongoing technical partner, or a workshop for your team—I'd love to hear what you're working on.
Notes on voice AI, ML infrastructure, and building in public.
I participated in the University Of Maryland's Technica 2022 hackathon, specifically diving into the research track that delved deep into the intricacies of AI-based translation...
Today, I'd like to take you through an intricate journey of constructing a data ETL pipeline, a cornerstone project during my tenure with the inaugural cohort of the DS4A Data Engineering program...
Hey there! I'm excited to share a story about a project that became one of the most enjoyable and enlightening experiences of my career -- building a Slack bot for Deepgram...