Theodore Blair

🟢𝑨𝒗𝒂𝒊𝒍𝒂𝒃𝒍𝒆 𝑵𝒐𝒘🟢

I am a Senior AI Engineer and Solutions Architect with 8+ years of experience designing and deploying intelligent automation systems, conversational agents, and secure video/voice streaming platforms for innovative startups and growing enterprises. My expertise brings together the latest in OpenAI (GPT-4/4o), Anthropic Claude, AWS AI/ML, Google Cloud AI, Livekit, and modern full-stack development to create scalable, compliant, and business-focused technology solutions.

From HIPAA-compliant healthcare apps to AI-powered onboarding for real estate, I specialize in building robust platforms that combine conversational and generative AI, voice, natural language understanding, video streaming, and advanced cloud infrastructure, empowering clients to achieve rapid digital transformation and measurable business ROI.

🟢 𝑺𝒐𝒍𝒖𝒕𝒊𝒐𝒏𝒔 & 𝑺𝒑𝒆𝒄𝒊𝒂𝒍𝒕𝒚 𝑨𝒓𝒆𝒂𝒔

Conversational & Voice AI Systems

• Omnichannel Conversational Agents: Architect and implement advanced chat/voice/multimodal agents using OpenAI, Claude, AWS Lex, Google Dialogflow, and custom RAG workflows by LangChain.
• VoiceBot & Call Automation: Engineered inbound/outbound phone bots and voice assistants with Vapi, Retell, AWS Connect & Polly, GCP Speech, and ElevenLabs—delivering frictionless customer service, scheduling, FAQs, and sales dialing.
• Natural Language Processing: Deploy sentiment analysis, summarization, and semantic search systems with GPT-4/Claude, BERT, spaCy, and cloud-hosted models.

Live Video & Avatar Streaming

• Livekit/Video Automation: Lead development of video meeting, webinar, and avatar streaming platforms for telehealth, education, live events, and virtual collaboration.
• Real-Time Media Processing: Integrated TTS/STT, real-time translation (AWS Polly/Transcribe, OpenAI Whisper, GCP Speech & Translate), and AI-powered captioning.

Generative, Predictive & Document AI

• Multi-Cloud Model Deployment: Orchestrate and fine-tune LLMs (GPT-4, Claude, Bedrock, Vertex AI), vision models, and document intelligence with AWS Textract, Comprehend, GCP AutoML, Document AI, and Rekognition.
• Automated Workflows: RAG-based AI for document ingestion, contract/data extraction, and semantic search across text, video, and audio.

Modern Cloud Architecture & Full Stack

• Cloud-Native Applications: Build secure, compliant (HIPAA, SOC2) systems on AWS (Lambda, API Gateway, SageMaker, DynamoDB, Aurora) and GCP (App Engine, Functions, Firestore).
• End-to-End App Development: Architect full-stack solutions with React.js, Next.js, Node.js, Python (Django, FastAPI), Flutter, and robust DevOps (Docker, CI/CD).

✅ 𝑻𝒂𝒏𝒈𝒊𝒃𝒍𝒆 𝑽𝒂𝒍𝒖𝒆 𝑫𝒆𝒍𝒊𝒗𝒆𝒓𝒆𝒅

• Reduced customer response time by 65% for a telehealth SaaS, building a multichannel AI support system (OpenAI + AWS Lex) and secure Livekit video/voice consults.
• Automated onboarding and document compliance, saving 1,000+ hours/year for a national real estate group using Claude, AWS Textract, and GCP Document AI integrations.
• Launched a music education platform enabling avatar-driven live classes with instant AI voice translation (Livekit + OpenAI + Google Speech), resulting in a 4.9-star user satisfaction.
• Enabled a 45% jump in user engagement for a SaaS startup via chat, voice, and video streaming with multilingual support and generative AI-powered Q&A (Claude, OpenAI, AWS, GCP).
• Ensured 99.99% uptime and regulatory compliance for corporate clients by leveraging secure multi-cloud architectures for sensitive healthcare and finance workflows.

🛠️ 𝑻𝒆𝒄𝒉𝒏𝒊𝒄𝒂𝒍 𝑺𝒌𝒊𝒍𝒍𝒔 & 𝑻𝒐𝒐𝒍𝒔

• LLMs & NLP: OpenAI GPT-4/4o, ChatGPT, Anthropic Claude 3, AWS Bedrock/Lex/Comprehend, Vertex AI, LangChain, CrewAI, RAG, BERT, spaCy
• Voice & Streaming: Livekit, Vapi, Retell, Twilio, AWS Connect/Chime, ElevenLabs, Whisper, Polly, Transcribe, GCP Speech-to-Text/Translate
• Generative/Document AI: AWS Textract, Rekognition, SageMaker | GCP Vision, AutoML, Document AI
• Cloud Platforms: AWS (Lambda, API Gateway, S3, DynamoDB, Aurora, SageMaker), GCP (App Engine, Firestore, Functions, Dialogflow, Storage)
• Web/Mobile Frameworks: React.js, Next.js, Flutter, Node.js, Python (Django, FastAPI), Go, Docker, CI/CD, Firebase, Supabase
• Integration/Automation: REST, GraphQL, Zapier, Make.com, n8n, secure API design
• Data: PostgreSQL, DynamoDB, Aurora, Firestore, MongoDB

🤝 𝐑𝐞𝐚𝐝𝐲 𝐭𝐨 𝐅𝐮𝐭𝐮𝐫𝐞-𝐏𝐫𝐨𝐨𝐟 𝐘𝐨𝐮𝐫 𝐁𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐰𝐢𝐭𝐡 𝐌𝐨𝐝𝐞𝐫𝐧 𝐀𝐈 & 𝐀𝐮𝐭𝐨𝐦𝐚𝐭𝐢𝐨𝐧?

Let’s discuss how intelligent AI agents, real-time voice/video solutions, and robust cloud deployments can add measurable value to your company. Contact me to start your next project with confidence!

Keywords: OpenAI, Claude, AWS AI, Google Vertex AI, Lex, Bedrock, Livekit, Voicebot, Video Streaming, LangChain, RAG, Document AI, Automation, HIPAA, SaaS, Reactive Apps, Compliance

Self Employed, Senior Software Engineer 10/2025 – Present

•Architect and deploy real-time voice AI agents using GPT-4/5, LiveKit, WebRTC, Whisper, and ElevenLabs.

•Designed HIPAA-compliant streaming infrastructure serving 12,000+ MAU, achieving 4.8/5 call quality satisfaction.

•Built adaptive dialogue pipelines with VAD, ASR → LLM → TTS, improving automation accuracy by 40%.

•Integrated voice AI into healthcare workflows—clinical inquiries, scheduling, intake, and triage—reducing manual effort by 45%.

•Delivered Retrieval-QA, automated note generation, and operational workflow orchestration.

Tech: Python, C#, Angular, TypeScript, FastAPI, NestJS, PostgreSQL, AWS (Lambda, API Gateway), Pinecone, LangChain, Bedrock, LiveKit

Striveworks, LLC, Senior Software Engineer 09/2024 – 09/2025 | Phoenix, AZ 

•Led development of LLM-powered collaboration tools and secure healthcare automation systems.

•Optimized WebRTC + LiveKit streaming for low-latency interactions across web + mobile clients.

•Launched data-driven platforms enabling enterprise AI adoption across 10+ clients.

•Built and maintained event-driven microservices ensuring reliable scaling and compliance.

Tech: React, TypeScript, Python, Kubernetes, PostgreSQL, AWS, C#

Azumo, Software Engineer 02/2021 – 08/2024 | San Francisco, CA

•Built Generative AI solutions for enterprise workflows, including automatic email drafting, document summarization, and visual content generation.

•Designed internal automation systems that cut operational effort by 35% in support and onboarding teams.

•Developed voice-interactive product features using ASR + TTS to enhance accessibility and engagement.

•Integrated AI microservices into production SaaS environments with secure data handling.

Tech: Generative AI APIs, Diffusion Models, FastAPI, React, Docker, PostgreSQL, TTS/STT, Twilio, n8n

A3Logics, Software Engineer 08/2017 – 01/2021 | Williston, ND

•Designed and deployed AI-generated video content systems supporting automated avatar animation, voice-to-character syncing, and rapid media localization for global audiences

•Built script-to-character generation workflows enabling marketing and e-learning teams to create high-quality narrative content without production staff

•Developed real-time preview and cloud rendering pipelines, reducing creative iteration and delivery timelines by 60%

•Implemented secure backend architecture for media processing, user attribution, and role-based access control

•Partnered closely with creative and product teams to convert storytelling requirements into reliable, scalable digital experiences

Tech: TypeScript, React, Node.js, Python, Firebase, FFmpeg, OpenCV, Three.js, Avatar APIs (Hedra, Tavus, BP, DID, HeyGen, etc ),CI/CD, WebSockets, REST APIs, AWS MediaConvert

B.S. Computer Science, San Francisco State University 08/2013 – 08/2017