I'm a Senior AI Full-Stack Engineer with 8+ years of experience building production-grade, Python-based AI systems and scalable cloud platforms. I specialize in LLMs, RAG pipelines, vector databases, and real-time voice/speech-to-text applications.
My work spans the full stack from low-latency FastAPI backends and WebSocket streaming services to modern React/Next.js frontends and I've shipped systems trusted by thousands of users in healthcare, federal, and enterprise environments.
- 🧠 Deep expertise in Generative AI, LangChain/LangGraph, and multi-agent workflows
- 🎙️ Built real-time voice AI pipelines with Whisper, Deepgram, LiveKit, and ElevenLabs
- 🏥 Delivered HIPAA-compliant clinical AI tools that cut documentation time by 40%
- ☁️ Deployed at scale on AWS SageMaker/Bedrock, Azure OpenAI, and GCP Vertex AI
Frontend
Backend
AI & Machine Learning
Voice & Conversational AI
Cloud & DevOps
- 🏥 Built multimodal, voice-enabled AI clinical assistants (Whisper + Deepgram + LiveKit) serving 10,000+ monthly therapy sessions
- 📄 Generated SOAP notes & session summaries that reduced clinician documentation time by 40%
- 💰 Reduced AI inference costs by 40% deploying on AWS SageMaker + Bedrock at millions of monthly requests
- 🔒 Designed HIPAA-compliant voice & text pipelines with PHI-safe data architecture
- 🏛️ Modernized federal facility management systems tracking 5,000+ assets across multi-site operations
- ⚡ Delivered low-latency real-time transcription and concurrent audio sessions at production scale
- 📈 Accelerated triage workflows and reduced provider documentation time by 30–45% with LLM-powered clinical tools
"Building reliable AI systems that solve real problems at production scale."