Skip to content
View Tylarcam's full-sized avatar
🎯
Focusing
🎯
Focusing
7 followers · 15 following

Achievements

Achievement: QuickdrawAchievement: Pull SharkAchievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pull SharkAchievement: YOLO

Highlights

  • Pro

Block or report Tylarcam

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tylarcam/README.md

Hi I am Tylar

Applied AI engineer who ships production LLM/ML systems for real users.

🎯 Focus

Production AI Deployment | Foundation Model Integration | AI Education

I design and validate AI systems that solve real problems—from model evaluation frameworks at Handshake to teaching AI fundamentals at Columbia to deploying generative models in production.

💼 Current Work

  • AI Instructor @ Columbia University (Fall 2025 - Spring 2026)
    Teaching Python, AI tooling, and production workflows to justice-impacted engineers via Justice Through Code program

  • AI Model Validation @ Handshake (Aug 2025 - Present)
    Designed evaluation frameworks for multi-modal AI models, improving accuracy 30% through systematic prompt engineering and QA protocols

🚢 Recent Deployments

TuneStory ✅ Shipped 2025

Applied AI music product integrating Meta MusicGen via Modal cloud infrastructure.
Stack: MusicGen, Modal, Supabase, Gemini, TypeScript
Focus: Controllable AI generation with preserved creative intent

Key decisions:

  • Chose Modal over ad-hoc GPU hosting for reproducibility + scalability
  • Structured generation as modular pipelines for creative iteration
  • Designed system to support future education use cases

Demo Video | GitHub

Other Production Projects

  • Spec_Tracer - AI-powered UI debugging tool with precision context capture
  • jarvis_voice_agent - Multimodal voice control system (AssemblyAI + ElevenLabs)
  • audio_transcriber - Speech-to-text pipeline with timestamps

🛠 Technical Stack

AI/ML: TensorFlow, HuggingFace, Claude/LLM APIs, MusicGen, Prompt Engineering
Backend: Python, TypeScript/React, Node.js, Modal, Supabase
Data: Pandas, NumPy, SQL, data validation frameworks
Tools: Git, Docker, Notion, Figma

📚 Background

PhD candidate in Interactive Arts & Technology @ Simon Fraser University
Research focus: Multimodal AI systems and human-AI interaction
Teaching: AI literacy, Python fundamentals, production ML workflows

📫 Connect

💡 Currently seeking: AI Product Manager or Applied AI Engineering roles where I can embed with teams to solve customer problems and own problem-to-deployment cycles.

Pinned Loading

  1. tunestory tunestory Public

    Production AI music platform with controllable generation. Deployed MusicGen via Modal cloud infrastructure for music education. TypeScript, Modal, Supabase, Gemini - shipped to real users in 2025

    TypeScript

  2. Spec_Tracer Spec_Tracer Public

    AI-powered UI debugging tool with precision context capture to eliminate unwanted AI changes. Production React/TypeScript app solving the problem of LLM overwriting in dev workflows.

    TypeScript

  3. audio_Transcriber audio_Transcriber Public

    Production Python pipeline for speech-to-text with timestamp extraction. Leverages AssemblyAI API for accurate transcription - demonstrates AI service integration and data processing workflows.

    Python

  4. jarvis_voice_agent jarvis_voice_agent Public

    Real-time multimodal voice agent integrating AssemblyAI speech recognition + ElevenLabs synthesis. Python-based system exploring voice-first AI interaction patterns for production deployment.

    Python