About

Creative
Design
Technologist
Creator
Producer.

Debayan Mukherjee

Creative Technologist, Generative AI Producer, Design thinker, UX Researcher, Creative Director and Producer with 12+ years of production-grade experience spanning multimodal content, enterprise creative pipelines, and interactive systems. Completed MS in Media Arts & Sciences at Arizona State University, with concentration in multi-modal generative AI. Former Creative Manager at Amazon across Middle East, India, Australia, and Singapore markets.

Gen·AI Production ComfyUI Pipelines Creative Leadership Interactive Systems Computer Vision 10+ Years Amazon ASU Researcher
Technical Skills
Languages & Frameworks
  • Python — Flask, ML inference scripts, pipeline automation
  • JavaScript / TypeScript — React 18, Redux, Tailwind CSS, Axios, WebSockets
  • Node.js — workflow automation & middleware
  • Swift / SwiftUI — iOS dev; RealityKit, ARKit, SceneKit, SpriteKit
  • C# / Unity — game systems, NavMesh AI
Gen·AI Image, Video & Motion
  • ComfyUI — node-based pipelines; sampler/VAE/preprocessor chaining
  • Stable Diffusion (SD 1.5, SDXL), Flux — checkpoint management, model merging
  • ControlNet — depth, canny, openpose; multi-ControlNet stacking
  • LoRA — dataset curation, training config, concept & style model authoring
  • AnimateDiff, SVD — image-to-video & text-to-video pipeline construction
  • Commercial: Sora, Veo, Kling · Audio: Suno, ElevenLabs
LLMs & RAG Pipelines
  • LangChain, OpenAI / Gemini / Claude APIs — prompt templating, chain construction
  • Ollama, LM Studio — local model deployment
  • FAISS + Hugging Face — vector search & RAG pipelines
  • Docker — containerization for ML services
ML & Computer Vision
  • PyTorch, Torchvision — model inference & training scripts
  • OpenCV — CV pipelines, keyframe extraction, object detection
  • YOLO (Ultralytics) — real-time segmentation & detection
  • ResNet-18, CLIP (ViT-B/32), SAM3 — embedding, classification, segmentation
  • Librosa, scikit-learn, NumPy, Pillow
Post-Production & Design
  • DaVinci Resolve — compositing, color, audio mixing, caption workflows
  • Adobe Creative Suite — Premiere Pro, After Effects, Photoshop, Illustrator
  • Figma, Blender, Capture One, OBS Studio
  • Git — version control for code, workflows & prompt systems
Creative Fundamentals
  • Composition, lighting design, motion direction, typography, sound design
  • Visual storytelling & studio/on-location photo/video production
  • UX sensibility and user-centred design thinking
  • Brand guidelines, safety guardrails for AI-generated media
Education
Arizona State University
M.S. Media Arts
& Sciences
2024 – 2026 · Concentration: Multi-modal Generative Art
National Institute of Fashion Technology (NIFT)
Bachelor of
Design
2009 – 2013 · Concentration: Fashion Design
Contact
LET'S
WORK
TOGETHER.
LinkedIn ↗ GitHub ↗
✓ Message sent — I'll be in touch soon.
Something went wrong. Please email me directly.