- π I'm an AI Developer with a passion for building LLM applications, speech interfaces, and real-time computer vision systems.
- π§ I work on RAG-based QA bots, voice-to-voice assistants, emotion detection, and sports player re-identification.
- β‘ Try turning complex research ideas into production-ready systems β even under tight deadlines.
- LLM & NLP: OpenAI API, LangChain, Pinecone, RAG, prompt engineering
- Speech: Real-time speech recognition, TTS, emotion classification
- Vision: YOLOv8/YOLOv11, DeepSORT, ByteTrack, image forgery detection
- Backend: FastAPI, Flask, REST APIs
- Tools: Streamlit, Docker, Git, GitHub Actions
- Languages: Python, JavaScript
Project | Description | Tech Stack |
---|---|---|
π§ Retail RAG QA Bot | Search retail documents using RAG + OpenAI + Pinecone | LangChain, FastAPI, Streamlit |
π Lead Scoring Engine | Classifies leads with ML + LLM re-ranking | FastAPI, GradientBoosting, React |
β½ Soccer Player Re-ID | Tracks players in a video using YOLOv11 + ByteTrack | CV, Tracking, Re-ID |
ποΈ Speech Emotion Detection | Classifies real-time voice emotions using deep learning | Streamlit, Deep Learning |
π΅οΈ Image Forgery Detection | Detects tampered images using VGG16, ResNet, MobileNet | CNNs, Keras |
- πΌ LinkedIn
- π§ Email: [email protected]
Built with β€οΈ by Divyansh Gautam