👋 Hi, I'm Animikh! I specialize in building and scaling end-to-end Machine Learning Systems.
- 🔭 Currently a Computer Vision & ML Engineer at Moultrie, developing next-gen CV algorithms for wildlife monitoring
- 🎓 MS in AI from Boston University – research focused on end-to-end Autonomous Driving at the H2X Lab
- 📝 Published at IROS '25 – IEEE/RSJ International Conference on Intelligent Robots and Systems
- 👨💻 Previously CV Engineer & Lead at Wobot.ai – built real-time video analytics from the ground up and scaled it globally
- 🌱 Core interests: Computer Vision, Multi-Modal AI, and Software Engineering
- 🌐 Personal website: animikh.me
- 💬 Always up for a good chat! Find me on X and LinkedIn
| 💰 Cost Savings | ⚡ Performance | 🎯 Accuracy | 🌍 Scale |
|---|---|---|---|
| $1M+/year saved via ML pipeline overhaul | 6× faster inference with NVIDIA Triton | +16.4% mAP on Animal Detection | 20,000+ cameras deployed globally |
| Year | Paper | Venue | Role |
|---|---|---|---|
| 2025 | Scalable Offline Metrics for Autonomous Driving · IEEE Xplore | IROS 2025 (IEEE) | First Author |
| 2024 | Towards Closing the Generalization Gap in Autonomous Driving | MS Thesis, Boston University | First Author |
| 2024 | Generative AI, Human Creativity, and Art | PNAS Nexus | Acknowledgement |
| 2022 | LatentGAN Autoencoder: Learning Disentangled Latent Distribution | arXiv | Co-Author |
| 2019 | Sentiment Analysis of Restaurant Reviews Using Machine Learning Techniques | ICERECT / Springer · 🏆 Best Paper Award | Co-Author |
| 2019 | Encoding Web-based Data for Efficient Storage in ML Applications | ICINPRO (IEEE) | First Author |
| 2018 | Analysis of Customer Opinion Using ML and NLP Techniques | IJASSR | Co-Author |
| 2018 | Sales-forecasting of Retail Stores Using ML Techniques | CSITSS (IEEE) | Co-Author |
| Project | Stack | Description |
|---|---|---|
| 📜 Site2LLM | Chrome Extension | Converts any website to neatly structured Markdown in one click |
| 📝 DigitizeMyNotes | LLMs · OCR · RAG | Converts handwritten notes to searchable digital text with AI chat, math recognition & export |
| 🎬 Video Search | React · Qdrant · VideoPrism | AI-powered semantic video discovery — find videos by describing what you're looking for |
| 🖼️ Image Search | React · Qdrant · CLIP | AI-powered semantic image discovery — find visually similar content from natural language descriptions |
| 🎨 Wallpaper AI | Stable Diffusion · GenAI | Generates high-quality 4K wallpapers from text prompts with enhancement |
| 🚗 Autonomous Driving | PyTorch · CARLA | End-to-end CIL in a real-world model city · Video |
| 🌌 3D Text2LIVE | NeRF · Gen AI | 3D appearance editing of objects via text prompts |
| 🛡️ Real-Time Face Blur | OpenVINO · Edge AI | CPU-optimized privacy-preserving face anonymization |
| 🏍️ Helmet Detector | YOLOv3 | Helmetless rider + license plate detection with synthetic data |
| 🏎️ RL Racer | Double DQN · RL | Racing agent trained on OpenAI Gym CarRacing-v0 |
| 🧠 Zero-Code Trainer | Docker · Streamlit | No-code model training toolkit (AutoML) |
- 🗓️ Co-Organizer — Boston Computer Vision AIR (AI, Autonomy & Robotics) — monthly meetups for 50–90+ participants from academia and industry; past events include AI-Enabled Robotics, Autonomous Vehicles, Navigation Beyond GPS, and more
- 📖 Manuscript Reviewer — Manning Publications · Journal of Open Source Software (JOSS) · GTC 2025 · ICCCT 2025 · ICCI 2024
⭐ If you find any of my repositories useful, consider giving them a star!